@misc{BeimGrabenRoemerMeyeretal., author = {Beim Graben, Peter and R{\"o}mer, Ronald and Meyer, Werner and Huber, Markus and Wolff, Matthias}, title = {Reinforcement learning of minimalist numeral grammars}, series = {10th IEEE International Conference on Cognitive Infocommunications (CogInfoCom), Naples, Italy}, journal = {10th IEEE International Conference on Cognitive Infocommunications (CogInfoCom), Naples, Italy}, isbn = {978-1-7281-4793-2}, issn = {2380-7350}, doi = {10.1109/CogInfoCom47531.2019.9089924}, pages = {13}, abstract = {Speech-controlled user interfaces facilitate the operation of devices and household functions to laymen. State-of-the-art language technology scans the acoustically analyzed speech signal for relevant keywords that are subsequently inserted into semantic slots to interpret the user's intent. In order to develop proper cognitive information and communication technologies, simple slot-filling should be replaced by utterance meaning transducers (UMT) that are based on semantic parsers and a mental lexicon, comprising syntactic, phonetic and semantic features of the language under consideration. This lexicon must be acquired by a cognitive agent during interaction with its users. We outline a reinforcement learning algorithm for the acquisition of the syntactic morphology and arithmetic semantics of English numerals, based on minimalist grammar (MG), a recent computational implementation of generative linguistics. Number words are presented to the agent by a teacher in form of utterance meaning pairs (UMP) where the meanings are encoded as arithmetic terms. Since MG encodes universal linguistic competence through inference rules, thereby separating innate linguistic knowledge from the contingently acquired lexicon, our approach unifies generative grammar and reinforcement learning, hence potentially resolving the still pending Chomsky-Skinner controversy.}, language = {en} } @misc{RoemerbeimGrabenHuberetal., author = {R{\"o}mer, Ronald and beim Graben, Peter and Huber, Markus and Klimczak, Peter and Wirsching, G{\"u}nther and Wolff, Matthias}, title = {Die Welt ist nicht genug! Man muss auch {\"u}ber sie sprechen k{\"o}nnen}, series = {Elektronische Sprachsignalverarbeitung 2020 : Tagungsband der 31. Konferenz Magdeburg, 4. - 6. M{\"a}rz 2020}, journal = {Elektronische Sprachsignalverarbeitung 2020 : Tagungsband der 31. Konferenz Magdeburg, 4. - 6. M{\"a}rz 2020}, editor = {Wendemuth, Andreas and B{\"o}ck, Ronald and Siegert, Ingo}, publisher = {TUDpress}, address = {Dresden}, isbn = {978-3-95908-193-1}, issn = {0940-6832}, pages = {173 -- 184}, language = {de} } @misc{WolffRoemerTschoepeetal., author = {Wolff, Matthias and R{\"o}mer, Ronald and Tsch{\"o}pe, Constanze and Hentschel, Dieter}, title = {Verfahren und Vorrichtung zur Verhaltenssteuerung von Systemen}, language = {de} } @misc{RoemerbeimGrabenHuberLiebletal., author = {R{\"o}mer, Ronald and beim Graben, Peter and Huber-Liebl, Markus and Wolff, Matthias}, title = {Unifying Physical Interaction, Linguistic Communication, and Language Acquisition of Cognitive Agents by Minimalist Grammars}, series = {Frontiers in Computer Science}, journal = {Frontiers in Computer Science}, number = {4}, issn = {2624-9898}, doi = {10.3389/fcomp.2022.733596}, pages = {21}, abstract = {Cognitive agents that act independently and solve problems in their environment on behalf of a user are referred to as autonomous. In order to increase the degree of autonomy, advanced cognitive architectures also contain higher-level psychological modules with which needs and motives of the agent are also taken into account and with which the behavior of the agent can be controlled. Regardless of the level of autonomy, successful behavior is based on interacting with the environment and being able to communicate with other agents or users. The agent can use these skills to learn a truthful knowledge model of the environment and thus predict the consequences of its own actions. For this purpose, the symbolic information received during the interaction and communication must be converted into representational data structures so that they can be stored in the knowledge model, processed logically and retrieved from there. Here, we firstly outline a grammar-based transformation mechanism that unifies the description of physical interaction and linguistic communication and on which the language acquisition is based. Specifically, we use minimalist grammar (MG) for this aim, which is a recent computational implementation of generative linguistics. In order to develop proper cognitive information and communication technologies, we are using utterance meaning transducers (UMT) that are based on semantic parsers and a mental lexicon, comprising syntactic and semantic features of the language under consideration. This lexicon must be acquired by a cognitive agent during interaction with its users. To this aim we outline a reinforcement learning algorithm for the acquisition of syntax and semantics of English utterances. English declarative sentences are presented to the agent by a teacher in form of utterance meaning pairs (UMP) where the meanings are encoded as formulas of predicate logic. Since MG codifies universal linguistic competence through inference rules, thereby separating innate linguistic knowledge from the contingently acquired lexicon, our approach unifies generative grammar and reinforcement learning, hence potentially resolving the still pending Chomsky-Skinner controversy. btuktuminglear, btuktsptech, btuktcogsys}, language = {en} } @misc{MeyerBorislavovEckertetal., author = {Meyer, Werner and Borislavov, Borislav and Eckert, Friedrich and Richter, Christian and R{\"o}mer, Ronald and Beim Graben, Peter and Huber, Markus and Wolff, Matthias}, title = {Formalisierung und Implementierung einer adaptiven kognitiven Architektur unter Verwendung von Strukturdiagrammen}, series = {Elektronische Sprachsignalverarbeitung 2021 : Tagungsband der 32. Konferenz Berlin, 3.-5. M{\"a}rz 2021}, journal = {Elektronische Sprachsignalverarbeitung 2021 : Tagungsband der 32. Konferenz Berlin, 3.-5. M{\"a}rz 2021}, editor = {Hillmann, Stefan and Weiss, Benjamin and Michael, Thilo and M{\"o}ller, Sebastian}, publisher = {TUDpress}, address = {Dresden}, isbn = {978-3-959082-27-3}, issn = {0940-6832}, pages = {67 -- 76}, abstract = {Das Fachgebiet der Kognitiven Technischen Systeme zeichnet sich durch einen hohen Grad an Interdisziplinarit{\"a}t (z. B. Kenntnisse auf den Gebieten Biologie, Psychologie, Informatik und den Ingenieurwissenschaften) aus. Nach wie vor besteht Bedarf an einer methodischen Darstellung des Fachgebietes, bei der die theoretische Durchdringung von Zusammenh{\"a}ngen zwischen den verschiedenen Wissensgebieten zus{\"a}tzlich durch Anschaulichkeit unterst{\"u}tzt wird. Die vorliegende Arbeit stellt einen Fortschrittsbericht zur Realisierung eines Forschungs- und Experimentiersystems dar, mit dem wir dieses Anliegen unterst{\"u}tzen und {\"u}ber das wir erstmals konzeptionell in [1] berichtet haben. In diesem Beitrag folgen wir einem integrativen Ansatz zur Entwicklung einer kognitiven Architektur, mit der unter Verwendung repr{\"a}sentationaler Datenstrukturen adaptives Verhalten auf verschiedenen Zeitskalen sowie zwei wichtige Verhaltensprogramme f{\"u}r das Probleml{\"o}sen (Objektfindung, Exploration) auf der gemeinsamen Grundlage von Markov-Entscheidungsprozessen umgesetzt werden. Mit einem Kurzbericht zum Entwicklungsstand der physikalischen Experimentierumgebung und einer Zusammenfassung der bislang erreichten Ergebnisse beschließen wir den diesj{\"a}hrigen Beitrag.}, language = {de} } @misc{BeimGrabenHuberMeyeretal., author = {Beim Graben, Peter and Huber, Markus and Meyer, Werner and R{\"o}mer, Ronald and Wolff, Matthias}, title = {Vector Symbolic Architectures for Context-Free Grammars}, series = {Cognitive Computation}, volume = {14}, journal = {Cognitive Computation}, number = {2}, issn = {1866-9964}, doi = {10.1007/s12559-021-09974-y}, pages = {733 -- 748}, abstract = {Vector symbolic architectures (VSA) are a viable approach for the hyperdimensional representation of symbolic data, such as documents, syntactic structures, or semantic frames. We present a rigorous mathematical framework for the representation of phrase structure trees and parse trees of context-free grammars (CFG) in Fock space, i.e. infinite-dimensional Hilbert space as being used in quantum field theory. We define a novel normal form for CFG by means of term algebras. Using a recently developed software toolbox, called FockBox, we construct Fock space representations for the trees built up by a CFG left-corner (LC) parser. We prove a universal representation theorem for CFG term algebras in Fock space and illustrate our findings through a low-dimensional principal component projection of the LC parser state. Our approach could leverage the development of VSA for explainable artificial intelligence (XAI) by means of hyperdimensional deep neural computation.}, language = {en} } @misc{HuberLieblRoemerWirschingetal., author = {Huber-Liebl, Markus and R{\"o}mer, Ronald and Wirsching, G{\"u}nther and Schmitt, Ingo and beim Graben, Peter and Wolff, Matthias}, title = {Quantum-inspired Cognitive Agents}, series = {Frontiers in Applied Mathematics and Statistics}, journal = {Frontiers in Applied Mathematics and Statistics}, number = {8}, issn = {2297-4687}, doi = {10.3389/fams.2022.909873}, pages = {1 -- 31}, abstract = {The concept of intelligent agents is—roughly speaking—based on an architecture and a set of behavioral programs that primarily serve to solve problems autonomously. Increasing the degree of autonomy and improving cognitive performance, which can be assessed using cognitive and behavioral tests, are two important research trends. The degree of autonomy can be increased using higher-level psychological modules with which needs and motives are taken into account. In our approach we integrate these modules in architecture for an embodied, enactive multi-agent system, such that distributed problem solutions can be achieved. Furthermore, after uncovering some weaknesses in the cognitive performance of traditionally designed agents, we focus on two major aspects. On the one hand, the knowledge processing of cognitive agents is based on logical formalisms, which have deficiencies in the representation and processing of incomplete or uncertain knowledge. On the other hand, in order to fully understand the performance of cognitive agents, explanations at the symbolic and subsymbolic levels are required. Both aspects can be addressed by quantum-inspired cognitive agents. To investigate this approach, we consider two tasks in the sphere of Shannon's famous mouse-maze problem: namely classifying target objects and ontology inference. First, the classification of an unknown target object in the mouse-maze, such as cheese, water, and bacon, is based on sensory data that measure characteristics such as odor, color, shape, or nature. For an intelligent agent, we need a classifier with good prediction accuracy and explanatory power on a symbolic level. Boolean logic classifiers do work on a symbolic level but are not adequate for dealing with continuous data. Therefore, we demonstrate and evaluate a quantum-logic-inspired classifier in comparison to Boolean-logic-based classifiers. Second, ontology inference is iteratively achieved by a quantum-inspired agent through maze exploration. This requires the agent to be able to manipulate its own state by performing actions and by collecting sensory data during perception. We suggest an algebraic approach where both kinds of behaviors are uniquely described by quantum operators. The agent's state space is then iteratively constructed by carrying out unitary action operators, while Hermitian perception operators act as observables on quantum eigenstates. As a result, an ontology emerges as the simultaneous solution of the respective eigenvalue equations. Tags: btuktqiai; btuktcogsys; btukttheseus; btuktqtheseus}, language = {en} } @misc{MaierWolff, author = {Maier, Isidor Konrad and Wolff, Matthias}, title = {A Decomposition Algorithm for Numerals based on Arithmetics}, doi = {10.5281/zenodo.7501698}, pages = {1}, abstract = {Poster presentation for an idea to decompose numerals}, language = {en} } @misc{TschoepeKraljevskiDuckhornetal., author = {Tsch{\"o}pe, Constanze and Kraljevski, Ivan and Duckhorn, Frank and Wolff, Matthias}, title = {Sprachtechnologie und akustische Mustererkennung in der medizinischen Anwendung}, series = {16. Landeskonferenz „Digitalisierung im Gesundheitswesen" 2021}, journal = {16. Landeskonferenz „Digitalisierung im Gesundheitswesen" 2021}, pages = {9}, language = {de} } @misc{RoemerbeimGrabenHuberLiebletal., author = {R{\"o}mer, Ronald and beim Graben, Peter and Huber-Liebl, Markus and Wolff, Matthias}, title = {(Pre-)linguistic Problem Solving based on Dynamic Semantics}, series = {14th IEEE International Conference on Cognitive Infocommunications - CogInfoCom 2023, September 22-23, Budapest, Hungary}, journal = {14th IEEE International Conference on Cognitive Infocommunications - CogInfoCom 2023, September 22-23, Budapest, Hungary}, isbn = {979-8-3503-2565-2}, issn = {2473-5671}, doi = {10.1109/CogInfoCom59411.2023.10397487}, pages = {147 -- 152}, language = {en} } @misc{MaierKuhnBeisegeletal., author = {Maier, Isidor Konrad and Kuhn, Johannes and Beisegel, Jesse and Huber-Liebl, Markus and Wolff, Matthias}, title = {Minimalist Grammar: Construction without Overgeneration}, series = {arXiv}, journal = {arXiv}, doi = {10.48550/arXiv.2311.01820}, pages = {51}, abstract = {In this paper we give instructions on how to write a minimalist grammar (MG). In order to present the instructions as an algorithm, we use a variant of context free grammars (CFG) as an input format. We can exclude overgeneration, if the CFG has no recursion, i.e. no non-terminal can (indirectly) derive to a right-hand side containing itself. The constructed MGs utilize licensors/-ees as a special way of exception handling. A CFG format for a derivation A_eats_B↦∗peter_eats_apples, where A and B generate noun phrases, normally leads to overgeneration, e.\,g., i_eats_apples. In order to avoid overgeneration, a CFG would need many non-terminal symbols and rules, that mainly produce the same word, just to handle exceptions. In our MGs however, we can summarize CFG rules that produce the same word in one item and handle exceptions by a proper distribution of licensees/-ors. The difficulty with this technique is that in most generations the majority of licensees/-ors is not needed, but still has to be triggered somehow. We solve this problem with ϵ-items called \emph{adapters}.}, language = {en} } @misc{KuhnWolffBorislavov, author = {Kuhn, Johannes and Wolff, Matthias and Borislavov, Borislav}, title = {Epsilon-Verarbeitung bei Minimalistischen Grammatiken f{\"u}r Zahlen}, series = {Elektronische Sprachsignalverarbeitung, Tagungsband der 35. Konferenz, 06.-08.03.2024, Regensburg}, journal = {Elektronische Sprachsignalverarbeitung, Tagungsband der 35. Konferenz, 06.-08.03.2024, Regensburg}, publisher = {TUDpress}, address = {Dresden}, isbn = {978-3-95908-325-6}, issn = {0940-6832}, pages = {78 -- 85}, abstract = {Um bei Minimalistischen Grammatiken (MG) {\"U}bergenerierung zu vermeiden, kann man Eintr{\"a}ge mit leeren Exponenten (ε-Eintr{\"a}ge) verwenden. Ein Eintrag besteht aus einem Exponenten, der die {\"A}ußerung oder Schrift eines Wortes repr{\"a}sentiert, einer Merkmalsliste, welche die Syntax kodiert und einem λ-Ausdruck, der die Semantik repr{\"a}sentiert. Leere Eintr{\"a}ge f{\"u}hren allerdings zu einer schlechteren Verwendbarkeit der Grammatik f{\"u}r das Parsen. Die vorliegende Arbeit wird ein Umformungsalgorithmus f{\"u}r MGs vorstellen, sodass die Anzahl der ε-Eintr{\"a}ge verringert werden kann, um sie wieder f{\"u}r Parser verwendbar zu machen. Hierzu werden die ε-Eintr{\"a}ge mit den anderen Eintr{\"a}gen vorverarbeitet und dadurch neue Eintr{\"a}ge geschaffen. Die nun {\"u}berfl{\"u}ssigen ε-Eintr{\"a}ge k{\"o}nnen dann problemlos entfernt werden. Der Algorithmus wurde anhand von {\"u}ber 260 Zahlwortgrammatiken getestet.}, language = {de} } @misc{KuhnWolffMaier, author = {Kuhn, Johannes and Wolff, Matthias and Maier, Isidor Konrad}, title = {Wortgenerator f{\"u}r Minimalistische Grammatiken}, series = {Elektronische Sprachsignalverarbeitung, Tagungsband der 36. Konferenz, 05.-07.03.2025, Halle/Saale}, journal = {Elektronische Sprachsignalverarbeitung, Tagungsband der 36. Konferenz, 05.-07.03.2025, Halle/Saale}, editor = {Grawunder, Sven}, publisher = {TUDpress}, address = {Dresden}, isbn = {978-3-95908-803-9}, issn = {0940-6832}, pages = {27 -- 34}, abstract = {Um eine bidirektionale Verarbeitung von Sprache zu realisieren, ist es von Vorteil den gleichen Sprachformalismus f{\"u}r das Parsen und die Generierung zu verwenden. F{\"u}r Minimalistische Grammatiken gibt es eine ausgepr{\"a}gte Literatur zu Parsern, aber noch keine Ver{\"o}ffentlichung zu Generatoren. Diese Arbeit stellt einen ersten Generator vor, der mittels Minimalistischer Grammatiken und λ-Ausdr{\"u}cken, S{\"a}tze erzeugt. Der hier vorgestellte Generator kann entgegen manchen anderen Generatoren, von anderen Grammatikformalismen, mit ε-Regeln arbeiten.}, language = {de} } @misc{HuberLieblRosenowRoemeretal., author = {Huber-Liebl, Markus and Rosenow, Tillmann and R{\"o}mer, Ronald and Wirsching, G{\"u}nther and Wolff, Matthias}, title = {It all starts with a little difference : tensors as data and code.}, series = {Elektronische Sprachsignalverarbeitung 2025 : Tagungsband der 36. Konferenz Halle/Saale, 5.-7. M{\"a}rz 2025}, journal = {Elektronische Sprachsignalverarbeitung 2025 : Tagungsband der 36. Konferenz Halle/Saale, 5.-7. M{\"a}rz 2025}, editor = {Grawunder, Sven}, publisher = {TUDpress}, address = {Dresden}, isbn = {978-3-95908-803-9}, issn = {0940-6832}, pages = {170 -- 179}, abstract = {We further promote the idea of quantum inspiration and propose to equip cognitive systems not only with tensors for data representation but also for operation representation. We argue that these are two sides of the same coin. For experimental symbolic algorithms we introduce a suitable testbed and give its proper specification. We formalize our method of behavioural control with tensor algebra and discuss its implementation for our physical testbed realization.}, language = {en} } @misc{MaierRosenowTuurietal., author = {Maier, Isidor Konrad and Rosenow, Tillmann and Tuuri, Okko and Wolff, Matthias}, title = {Frequency-magnitude relation of numeral words based on search-engine results}, series = {Elektronische Sprachsignalverarbeitung, Tagungsband der 36. Konferenz, 05.-07.03.2025, Halle/Saale}, journal = {Elektronische Sprachsignalverarbeitung, Tagungsband der 36. Konferenz, 05.-07.03.2025, Halle/Saale}, editor = {Grawunder, Sven}, publisher = {TUDpress}, address = {Dresden}, isbn = {978-3-95908-803-9}, issn = {0940-6832}, pages = {51 -- 60}, abstract = {We googled various numeral words from 28 languages. Different approaches for the description of the data were investigated. In all of the 28 languages, the found frequency-magnitude dependence fits better to a power law than to an exponential law. The result can be used to distinguish grammatically correct from incorrect numerals based on the prediction of search results.}, language = {en} } @inproceedings{WolffSchubertHoffmannetal., author = {Wolff, Matthias and Schubert, R. and Hoffmann, R{\"u}diger and Tsch{\"o}pe, Constanze and Schulze, E. and Neun{\"u}bel, H.}, title = {Experiments in Acoustic Structural Health Monitoring of Airplane Parts}, series = {IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP 2008), 30.3.-4.4.2008, Las Vegas, USA}, booktitle = {IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP 2008), 30.3.-4.4.2008, Las Vegas, USA}, publisher = {IEEE}, isbn = {978-1-4244-1483-3}, doi = {10.1109/ICASSP.2008.4518040}, pages = {2037 -- 2040}, language = {en} } @inproceedings{StrechaWolffDuckhornetal., author = {Strecha, Guntram and Wolff, Matthias and Duckhorn, Frank and Wittenberg, S{\"o}ren and Tsch{\"o}pe, Constanze}, title = {The HMM synthesis algorithm of an embedded unified speech recognizer and synthesizer}, series = {Proceedings of the Annual Conference of the International Speech Communication Association 2009, Interspeech 2009, 6 - 10 September, 2009, Brighton, UK}, booktitle = {Proceedings of the Annual Conference of the International Speech Communication Association 2009, Interspeech 2009, 6 - 10 September, 2009, Brighton, UK}, publisher = {ISCA}, address = {Brighton}, pages = {1763 -- 1766}, language = {en} } @misc{PuschCherifFarooqetal., author = {Pusch, T. and Cherif, Chokri and Farooq, Aamir and Wittenberg, S{\"o}ren and Wolff, Matthias and Hoffmann, R{\"u}diger and Tsch{\"o}pe, Constanze}, title = {Fehlerfr{\"u}herkennung an Textilmaschinen mit Hilfe der K{\"o}rperschallanalyse}, series = {Melliand Textilberichte}, volume = {90}, journal = {Melliand Textilberichte}, number = {3}, issn = {0341-0781}, pages = {113 -- 115}, language = {de} } @inproceedings{WolffTschoepe, author = {Wolff, Matthias and Tsch{\"o}pe, Constanze}, title = {Pattern recognition for sensor signals}, series = {Proceedings of the IEEE Sensors Conference 2009, Christchurch, New Zealand, 25 - 28 October 2009}, booktitle = {Proceedings of the IEEE Sensors Conference 2009, Christchurch, New Zealand, 25 - 28 October 2009}, publisher = {IEEE}, address = {Piscataway, NJ}, isbn = {978-1-424-44548-6}, doi = {10.1109/ICSENS.2009.5398338}, pages = {665 -- 668}, language = {en} } @phdthesis{Wolff, author = {Wolff, Matthias}, title = {Akustische Mustererkennung}, publisher = {TUDpress}, address = {Dresden}, isbn = {978-3-942710-14-5}, pages = {XIV, 313}, language = {de} } @misc{LiKraljevskiMeyeretal., author = {Li, Huajian and Kraljevski, Ivan and Meyer, Paul and Tsch{\"o}pe, Constanze and Wolff, Matthias}, title = {YOLO-ICP : deep learning integrated pose estimation for bin-picking of multiple objects}, series = {2024 IEEE SENSORS, Proceedings, Kobe, Japan, 2024}, journal = {2024 IEEE SENSORS, Proceedings, Kobe, Japan, 2024}, publisher = {Institute of Electrical and Electronics Engineers (IEEE)}, address = {Piscataway, New Jersey}, isbn = {979-8-3503-6351-7}, doi = {10.1109/SENSORS60989.2024.10784539}, pages = {1 -- 4}, abstract = {In this paper, we present a novel deep learning-integrated pipeline called YOLO-ICP that aims to estimate the six degree of freedom (6-DoF) pose of objects using RGB-D sensors and does not require pose labels to train deep learning networks. YOLO-ICP integrates a real-time object detection algorithm with a point cloud registration method to estimate the pose of multiple objects. We evaluated our approach by quantitatively comparing it with baseline models on the OccludedLINEMOD dataset. Experimental results illustrate that our approach outperforms baseline models in challenging scenarios with textureless and occluded objects. In particular, our pipeline shows superior performance when dealing with small and symmetric objects in terms of the ADD(-S) metric.}, language = {en} } @misc{KraljevskiDuckhornSobeetal., author = {Kraljevski, Ivan and Duckhorn, Frank and Sobe, Daniel and Tsch{\"o}pe, Constanze and Wolff, Matthias}, title = {Speech-to-text in upper sorbian : current state}, series = {Elektronische Sprachsignalverarbeitung 2025 : Tagungsband der 36. Konferenz Halle/Saale, 5.-7. M{\"a}rz 2025}, journal = {Elektronische Sprachsignalverarbeitung 2025 : Tagungsband der 36. Konferenz Halle/Saale, 5.-7. M{\"a}rz 2025}, editor = {Grawunder, Sven}, publisher = {TUDpress}, address = {Dresden}, isbn = {978-3-95908-803-9}, issn = {0940-6832}, pages = {109 -- 116}, abstract = {This study presents recent advancements in Upper Sorbian Speech-to-Text (STT) technology. We provide an overview of the Sorbian languages, the available speech and language resources, and the development of an STT system based on a traditional approach, which includes acoustic, pronunciation, and language modeling. Due to the scarcity of resources for Sorbian languages, our approach leverages sub-word and word-class modeling techniques. The word-class modeling is based on Finite-State Transducer definitions, which are applicable to both offline text parsing and integration into the decoding graph of the STT system. Word-class parsing is performed on the speech corpus and utilized for language modeling with complete words, sub-word units, or both. Additionally, the same definitions can be applied to Named Entity Recognition during the post-processing of recognized transcriptions. This approach significantly reduces out-of-vocabulary words and enables greater customization of the recognizer for domain-specific applications. The system was implemented for the real-time transcription of church sermon broadcasts in Upper Sorbian. The domain-specific system achieved performance comparable to fine-tuned OpenAI Whisper models developed also by other initiatives while also providing a resource-efficient solution with semantically tagged recognition results.}, language = {en} } @misc{KraljevskiDuckhornSobeetal., author = {Kraljevski, Ivan and Duckhorn, Frank and Sobe, Daniel and Tsch{\"o}pe, Constanze and Wolff, Matthias}, title = {Preserving Language Heritage Through Speech Technology: The Case of Upper Sorbian}, series = {Speech and Computer, SPECOM 2024, Belgrade, Serbia, 25-28 November 2024}, journal = {Speech and Computer, SPECOM 2024, Belgrade, Serbia, 25-28 November 2024}, editor = {Karpov, Alexey and Delic, Vlado}, publisher = {Springer Nature Switzerland, Cham}, isbn = {978-3-031-77960-2}, doi = {10.1007/978-3-031-77961-9_1}, pages = {3 -- 22}, abstract = {The modern world is facing a crisis with the rapid disappearance of endangered languages, which poses a serious threat to global cultural diversity. Speech Technologies and Artificial Intelligence present promising opportunities to address this crisis by supporting the documentation, revitalization, and everyday use of these vulnerable languages. However, despite recent and remarkable advancements in speech technology, significant challenges persist, particularly for languages with very limited resources and unique linguistic features. This paper details the development of Upper Sorbian speech technologies, focusing on the creation of a practical Speech-to-Text (STT) system as a versatile tool for language preservation. The study explores the current state of Sorbian languages and underscores collaborative efforts with the Foundation for the Sorbian People. Through a series of pilot and successive projects, each phase has contributed to the steady advancement of speech recognition modules and supporting tools, improving their performance, effectiveness and practical usability.}, language = {en} } @misc{SaeltzerTschoepeWolff, author = {Saeltzer, Gerhard and Tsch{\"o}pe, Constanze and Wolff, Matthias}, title = {Vorrichtung und Verfahren zur Bestimmung eines medizinischen Gesundheitsparameters eines Probanden mittels Stimmanalyse}, pages = {31}, abstract = {Eine Vorrichtung zur Bestimmung eines Gesundheitsparameters eines Probanden mittels Stimmauswertung umfasst eine Verarbeitungseinrichtung, die ausgebildet ist, um eine digitalisierte Sprechprobe des Probanden basierend auf individuellen Modellparametern auszuwerten, um eine Messinformation zu erhalten, die innerhalb eines Toleranzbereichs auf einem Momentanwert des Gesundheitsparameters des Probanden basiert, wobei die individuellen Modellparameter einen funktionalen Zusammenhang zwischen der Sprechprobe oder von der Sprechprobe abgeleiteten Sprechmerkmalen und einem zugeordneten, momentanen Gesundheitsparameter angeben.}, language = {de} } @misc{WolffRoemerTschoepeetal., author = {Wolff, Matthias and R{\"o}mer, Ronald and Tsch{\"o}pe, Constanze and Hentschel, Dieter}, title = {Method and Device for Controlling the Behavior of Systems}, language = {en} } @inproceedings{TschoepeWolff, author = {Tsch{\"o}pe, Constanze and Wolff, Matthias}, title = {Automatic decision making in SHM using hidden Markov models}, series = {18th International Conference on Database and Expert Systems Applications (DEXA 2007), Regensburg, September 3-7, 2007}, booktitle = {18th International Conference on Database and Expert Systems Applications (DEXA 2007), Regensburg, September 3-7, 2007}, publisher = {IEEE}, doi = {10.1109/DEXA.2007.138}, pages = {307 -- 311}, language = {en} } @misc{TschoepeWolffHoffmann, author = {Tsch{\"o}pe, Constanze and Wolff, Matthias and Hoffmann, R{\"u}diger}, title = {Akustische Mustererkennung f{\"u}r die ZfP}, series = {MP Materials Testing}, volume = {51}, journal = {MP Materials Testing}, number = {10}, issn = {0025-5300}, pages = {701 -- 704}, language = {de} } @incollection{KordonWolffTschoepe, author = {Kordon, Ulrich and Wolff, Matthias and Tsch{\"o}pe, Constanze}, title = {Mustererkennung f{\"u}r Sensorsignale}, editor = {Gerlach, Gerald}, publisher = {TUDpress}, address = {Dresden}, isbn = {978-3-941298-55-2}, pages = {69 -- 78}, language = {de} } @misc{TschoepeWolff, author = {Tsch{\"o}pe, Constanze and Wolff, Matthias}, title = {Statistical Classifiers for Structural Health Monitoring}, series = {IEEE sensors journal}, volume = {9}, journal = {IEEE sensors journal}, number = {11}, issn = {1530-437X}, doi = {10.1109/JSEN.2009.2019330}, pages = {1567 -- 1576}, language = {en} } @inproceedings{TschoepeWolff, author = {Tsch{\"o}pe, Constanze and Wolff, Matthias}, title = {Instrumentelle Bestimmung der Weichheit von Tissueprodukten}, series = {Forum Akustische Qualit{\"a}tssicherung 2010 der DGAQS, 03. und 04. November 2010 in Karlsruhe}, booktitle = {Forum Akustische Qualit{\"a}tssicherung 2010 der DGAQS, 03. und 04. November 2010 in Karlsruhe}, publisher = {DGaQs}, address = {Karlsruhe}, pages = {3-1 -- 3-3}, language = {de} } @inproceedings{TschoepeWolffHoffmann, author = {Tsch{\"o}pe, Constanze and Wolff, Matthias and Hoffmann, R{\"u}diger}, title = {Akustische Mustererkennung}, series = {DAGA 2011, 37. Jahrestagung f{\"u}r Akustik, D{\"u}sseldorf, 21. - 24. 3. 2011, Tagungsband "Fortschritte der Akustik"}, booktitle = {DAGA 2011, 37. Jahrestagung f{\"u}r Akustik, D{\"u}sseldorf, 21. - 24. 3. 2011, Tagungsband "Fortschritte der Akustik"}, editor = {Becker-Schweitzer, J{\"o}rg}, publisher = {Dt. Gesellschaft f{\"u}r Akustik}, address = {Berlin}, isbn = {978-3-939296-02-7}, pages = {345 -- 346}, language = {de} } @inproceedings{TschoepeWolff, author = {Tsch{\"o}pe, Constanze and Wolff, Matthias}, title = {Zur Formulierung von Hidden-Markov-Modellen als endliche Transduktoren}, series = {Elektronische Sprachsignalverarbeitung 2012, Tagungsband der 23. Konferenz, Cottbus, 29. - 31. August 2012}, booktitle = {Elektronische Sprachsignalverarbeitung 2012, Tagungsband der 23. Konferenz, Cottbus, 29. - 31. August 2012}, editor = {Wolff, Matthias}, publisher = {TUDpress}, address = {Dresden}, isbn = {978-3-942710-81-7}, pages = {120 -- 128}, language = {de} } @inproceedings{TschoepeJoneitDuckhornetal., author = {Tsch{\"o}pe, Constanze and Joneit, Dieter and Duckhorn, Frank and Hoffmann, R{\"u}diger and Strecha, Guntram and Wolff, Matthias}, title = {Sprachsteuerung f{\"u}r Mess- und Pr{\"u}fger{\"a}te}, series = {DGZfP-Jahrestagung 2011 Zerst{\"o}rungsfreie Materialpr{\"u}fung, 30. Mai - 1. Juni 2011, Bremen, Berichtsband}, booktitle = {DGZfP-Jahrestagung 2011 Zerst{\"o}rungsfreie Materialpr{\"u}fung, 30. Mai - 1. Juni 2011, Bremen, Berichtsband}, publisher = {DGZfP}, address = {Berlin}, isbn = {978-3-940283-33-7}, pages = {6}, language = {de} } @inproceedings{WolffTschoepeRoemeretal., author = {Wolff, Matthias and Tsch{\"o}pe, Constanze and R{\"o}mer, Ronald and Wirsching, G{\"u}nther}, title = {Subsymbol-Symbol-Transduktoren}, series = {Elektronische Sprachsignalverarbeitung 2013, Tagungsband, Bielefeld, 2013}, booktitle = {Elektronische Sprachsignalverarbeitung 2013, Tagungsband, Bielefeld, 2013}, editor = {Wagner, Petra}, publisher = {TUDpress}, address = {Dresden}, isbn = {978-3-94431-03-4}, pages = {197 -- 204}, language = {de} } @inproceedings{TschoepeWolffHoffmann, author = {Tsch{\"o}pe, Constanze and Wolff, Matthias and Hoffmann, R{\"u}diger}, title = {Anwendungen der akustischen Mustererkennung}, series = {Elektronische Sprachsignalverarbeitung 2013, Tagungsband, Bielefeld, 2013}, booktitle = {Elektronische Sprachsignalverarbeitung 2013, Tagungsband, Bielefeld, 2013}, editor = {Wagner, Petra}, publisher = {TUDpress}, address = {Dresden}, isbn = {978-3-94431-03-4}, pages = {205 -- 210}, language = {de} } @inproceedings{TschoepeWolffDuckhorn, author = {Tsch{\"o}pe, Constanze and Wolff, Matthias and Duckhorn, Frank}, title = {Zustands{\"u}berwachung von Magnetventilen anhand der Schaltger{\"a}usche}, series = {ZfP in Forschung, Entwicklung und Anwendung, Potsdam, 26. - 28. Mai 2014, DGZfP-Jahrestagung 2014}, booktitle = {ZfP in Forschung, Entwicklung und Anwendung, Potsdam, 26. - 28. Mai 2014, DGZfP-Jahrestagung 2014}, publisher = {DGZfP}, address = {Berlin}, isbn = {978-3-940283-61-0}, language = {de} } @incollection{WolffTschoepeRoemer, author = {Wolff, Matthias and Tsch{\"o}pe, Constanze and R{\"o}mer, Ronald}, title = {Quo vadis, UASR?}, series = {Systemtheorie Signalverarbeitung Sprachtechnologie}, booktitle = {Systemtheorie Signalverarbeitung Sprachtechnologie}, editor = {Mehnert, Dieter and Kordon, Ulrich and Wolff, Matthias}, publisher = {TUDpress}, address = {Dresden}, isbn = {978-3-944331-19-5}, pages = {276 -- 285}, language = {de} } @inproceedings{TschoepeWolff, author = {Tsch{\"o}pe, Constanze and Wolff, Matthias}, title = {Processing and evaluation of gear data using statistical classifiers}, series = {Proceedings of the 6th European Congress on Computational Methods in Applied Sciences and Engineering (ECCOMAS 2012), Vienna, Sep. 2012}, booktitle = {Proceedings of the 6th European Congress on Computational Methods in Applied Sciences and Engineering (ECCOMAS 2012), Vienna, Sep. 2012}, address = {Vienna}, isbn = {978-395-02481-9-7}, language = {en} } @misc{KraljevskiDuckhornJuetal., author = {Kraljevski, Ivan and Duckhorn, Frank and Ju, Yong Chul and Tsch{\"o}pe, Constanze and Richter, Christian and Wolff, Matthias}, title = {Acoustic Resonance Recognition of Coins}, series = {2020 IEEE International Instrumentation and Measurement Technology Conference (I2MTC), 25-28 May 2020, Dubrovnik, Croatia}, journal = {2020 IEEE International Instrumentation and Measurement Technology Conference (I2MTC), 25-28 May 2020, Dubrovnik, Croatia}, publisher = {IEEE Xplore}, isbn = {978-1-7281-4460-3}, doi = {10.1109/I2MTC43012.2020.9129256}, pages = {6}, abstract = {In this study, we compare different machine learning approaches applied to acoustic resonance recognition of coins. Euro-cents and Euro-coins were classified by the sound emerging when throwing the coins onto a hard surface.The used dataset is a representative example of a small data which was collected in carefully prepared experiments.Due to the small number of coin specimens and the count of the collected observations, it was interesting to see whether deep learning methods can achieve similarly or maybe even better classification performances compared with more traditional methods.The results of the multi-class prediction of coin denominations are presented and compared in terms of balanced accuracy and Matthews Correlation Coefficient metrics. The feature analysis methods combined with the employed classifiers achieved acceptable results, despite the relatively small dataset.}, language = {en} } @misc{KraljevskiDuckhornJuetal., author = {Kraljevski, Ivan and Duckhorn, Frank and Ju, Yong Chul and Tsch{\"o}pe, Constanze and Wolff, Matthias}, title = {Acoustic Resonance Testing of Glass IV Bottles}, series = {Artificial Intelligence Applications and Innovations : 16th IFIP WG 12.5 International Conference, AIAI 2020, Neos Marmaras, Greece, June 5-7, 2020, Proceedings, Part II}, volume = {Cham}, journal = {Artificial Intelligence Applications and Innovations : 16th IFIP WG 12.5 International Conference, AIAI 2020, Neos Marmaras, Greece, June 5-7, 2020, Proceedings, Part II}, editor = {Maglogiannis, Ilias and Iliadis, Lazaros S. and Pimenidis, Elias}, publisher = {Springer International Publishing}, isbn = {978-3-030-49186-4}, issn = {1868-4238}, doi = {10.1007/978-3-030-49186-4_17}, pages = {195 -- 206}, abstract = {In this paper, acoustic resonance testing on glass intravenous (IV) bottles is presented. Different machine learning methods were applied to distinguish acoustic observations of bottles with defects from the intact ones. Due to the very limited amount of available specimens, the question arises whether the deep learning methods can achieve similar or even better detection performance compared with traditional methods.}, language = {en} } @inproceedings{TschoepeDuckhornHuberetal., author = {Tsch{\"o}pe, Constanze and Duckhorn, Frank and Huber, Markus and Meyer, Werner and Wolff, Matthias}, title = {A Cognitive User Interface for a Multi-Modal Human-Machine Interaction}, series = {Speech and computer : 20th International Conference, SPECOM 2018, Leipzig, Germany, September 18-22, 2018, proceedings}, booktitle = {Speech and computer : 20th International Conference, SPECOM 2018, Leipzig, Germany, September 18-22, 2018, proceedings}, editor = {Karpov, Alexey and Jokisch, Oliver and Potapova, Rodmonga}, publisher = {Springer International Publishing}, address = {Cham}, isbn = {978-3-319-99578-6}, doi = {10.1007/978-3-319-99579-3}, pages = {707 -- 717}, language = {en} } @misc{DuckhornHuberMeyeretal., author = {Duckhorn, Frank and Huber, Markus and Meyer, Werner and Jokisch, Oliver and Tsch{\"o}pe, Constanze and Wolff, Matthias}, title = {Towards an Autarkic Embedded Cognitive User Interface}, series = {Proceedings Interspeech 2017, 20-24 August 2017, Stockholm}, journal = {Proceedings Interspeech 2017, 20-24 August 2017, Stockholm}, editor = {Lacerda, Francisco}, publisher = {ISCA}, doi = {10.21437/Interspeech.2017}, pages = {3435 -- 3436}, abstract = {ucuikt2015}, language = {en} } @inproceedings{TschoepeDuckhornRichteretal., author = {Tsch{\"o}pe, Constanze and Duckhorn, Frank and Richter, Christian and Bl{\"u}thgen, Peter and Wolff, Matthias}, title = {Intelligent Signal Processing on a Miniaturized Hardware Module}, series = {IEEE SENSORS Proceedings, Glasgow, Scotland, UK, Oct. 29 - Nov. 1, 2017}, booktitle = {IEEE SENSORS Proceedings, Glasgow, Scotland, UK, Oct. 29 - Nov. 1, 2017}, publisher = {IEEE}, address = {Piscataway, NJ}, isbn = {978-1-5090-1012-7}, doi = {10.1109/ICSENS.2017.8234023}, language = {en} } @inproceedings{TschoepeWolff, author = {Tsch{\"o}pe, Constanze and Wolff, Matthias}, title = {Mustererkennung in der technischen Diagnose}, series = {Tagungsband der 12. Tagung Technische Diagnostik 2016, 20.-21.10.2016, Hochschule Merseburg}, booktitle = {Tagungsband der 12. Tagung Technische Diagnostik 2016, 20.-21.10.2016, Hochschule Merseburg}, publisher = {Hochschule Merseburg}, address = {Merseburg}, isbn = {978-3-942703-64-2}, url = {http://nbn-resolving.de/urn:nbn:de:gbv:3:2-68977}, pages = {124 -- 125}, language = {de} } @inproceedings{TschoepeDuckhornRichteretal., author = {Tsch{\"o}pe, Constanze and Duckhorn, Frank and Richter, Christian and Bl{\"u}thgen, Peter and Wolff, Matthias}, title = {An embedded system for acoustic pattern recognition}, series = {IEEE SENSORS Proceedings, Glasgow, Scotland, UK, Oct. 29 - Nov. 1, 2017}, booktitle = {IEEE SENSORS Proceedings, Glasgow, Scotland, UK, Oct. 29 - Nov. 1, 2017}, publisher = {IEEE}, address = {Piscataway, NJ}, isbn = {978-1-5090-1012-7}, doi = {10.1109/ICSENS.2017.8234380}, pages = {3}, language = {en} } @inproceedings{TschoepeWolffSaeltzer, author = {Tsch{\"o}pe, Constanze and Wolff, Matthias and Saeltzer, G.}, title = {Estimating blood sugar from voice samples : a preliminary study}, series = {2015 International Conference on Computational Science and Computational Intelligence (CSCI 2015), Las Vegas, December 7-9, 2015}, booktitle = {2015 International Conference on Computational Science and Computational Intelligence (CSCI 2015), Las Vegas, December 7-9, 2015}, publisher = {IEEE}, doi = {10.1109/CSCI.2015.184}, pages = {804 -- 805}, language = {en} } @misc{TschoepeMuehleJuetal., author = {Tsch{\"o}pe, Constanze and M{\"u}hle, Maximilian and Ju, Yong Chul and Kraljevski, Ivan and Wolff, Matthias}, title = {K{\"u}nstliche Intelligenz in der ZfP - Welchen Beitrag kann KI in der ZfP leisten?}, series = {DGZfP-Jahrestagung 2021, 10.-11. Mai}, journal = {DGZfP-Jahrestagung 2021, 10.-11. Mai}, isbn = {978-3-947971-18-3}, pages = {17}, abstract = {K{\"u}nstliche Intelligenz zieht derzeit in alle Bereiche der Gesellschaft und des Lebens ein. Aber welchen Stellenwert hat sie momentan auf dem Gebiet der zerst{\"o}rungsfreien Pr{\"u}fung? Was kann KI leisten? Welche Herausforderungen m{\"u}ssen erfolgreich bew{\"a}ltigt werden? Gibt es das eine KI-Verfahren, welches prinzipiell f{\"u}r ZfP geeignet ist? Bei der Bauteil- und Materialpr{\"u}fung w{\"a}hrend und unmittelbar nach der Herstellung, der {\"U}berwachung von Verschleißteilen in Maschinen und Anlagen oder der Schadensdetektion an Bauteilen und Komponenten liefern ZfP-Verfahren Daten, die bewertet werden m{\"u}ssen. Obwohl inzwischen sehr leistungsf{\"a}hige Toolkits verf{\"u}gbar sind, erfordert der optimale Einsatz der KI f{\"u}r ein ZfP-Verfahren oftmals mehr. Die meisten Kunden m{\"o}chten nicht nur eine L{\"o}sung ihres Problems; sie wollen verstehen, warum die KI so und nicht anders entschieden hat, warum der Klassifikator das Bauteil einer bestimmten Klasse (z. B. gut/schlecht oder neuwertig/verschlissen/defekt) zugewiesen hat. Abh{\"a}ngig von der Klassifikationsaufgabe sowie der Art und der Anzahl der vorliegenden Daten kann ein geeignetes Verfahren bestimmt werden. Mit Methoden des maschinellen Lernens werden Modelle gebildet, welche die Basis f{\"u}r die KI-Verfahren zur Klassifikation bilden. Der Beitrag liefert einen {\"U}berblick {\"u}ber KI-Verfahren und deren Anwendungen in der zerst{\"o}rungsfreien Pr{\"u}fung. Zahlreiche Beispiele und Ergebnisse werden vorgestellt, um die Mannigfaltigkeit des Einsatzes in der ZfP und der bestehenden M{\"o}glichkeiten zu demonstrieren.}, language = {de} } @misc{KraljevskiRjelkaDuckhornetal., author = {Kraljevski, Ivan and Rjelka, Marek and Duckhorn, Frank and Tsch{\"o}pe, Constanze and Wolff, Matthias}, title = {Cross-Lingual Acoustic Modeling in Upper Sorbian - Preliminary Study}, series = {Elektronische Sprachsignalverarbeitung 2021 : Tagungsband der 32. Konferenz Berlin, 3.-5. M{\"a}rz 2021}, journal = {Elektronische Sprachsignalverarbeitung 2021 : Tagungsband der 32. Konferenz Berlin, 3.-5. M{\"a}rz 2021}, editor = {Hillmann, Stefan and Weiss, Benjamin and Michael, Thilo and M{\"o}ller, Sebastian}, publisher = {TUDpress}, address = {Dresden}, isbn = {978-3-959082-27-3}, issn = {0940-6832}, pages = {43 -- 50}, abstract = {In this paper, we present a preliminary study for acoustic modeling in Upper Sorbian, where a model of German was used in cross-lingual transfer learning. At first, we define the grapheme and phoneme inventories and map the target phonemes from the most similar German source equivalents. Phonetically balanced sentences for the recording prompts were selected from a combination of general and domain-specific textual data. The speech corpora with a total duration of around 11 hours was collected in controlled recording sessions involving an equal number of females, males, and children. The baseline acoustic model was employed to force-align the speech corpora given the knowledge-based phoneme mappings. How well the mappings were, was evaluated by the phoneme confusions in free-phoneme recognition. The new derived data-driven model with a reduced phoneme set was included in the adaptation and evaluation along with the baseline acoustic model. The model adaptation performance was cross-validated with the "Leave One Group Out" strategy. We observed major improvements in phoneme error rates after adaptation for the knowledge-based and data-driven phoneme mappings. The study confirmed the feasibility of transfer learning for acoustic model adaptation in the case of Upper Sorbian, at the same time demonstrating practical usability with a small vocabulary speech recognition application (Smart Lamp).}, language = {de} } @misc{KraljevskiDuckhornTschoepeetal., author = {Kraljevski, Ivan and Duckhorn, Frank and Tsch{\"o}pe, Constanze and Wolff, Matthias}, title = {Machine Learning for Anomaly Assessment in Sensor Networks for NDT in Aerospace}, series = {IEEE Sensors Journal}, volume = {21}, journal = {IEEE Sensors Journal}, number = {9}, issn = {1558-1748}, doi = {10.1109/JSEN.2021.3062941}, pages = {11000 -- 11008}, abstract = {We investigated and compared various algorithms in machine learning for anomaly assessment with different feature analyses on ultrasonic signals recorded by sensor networks. The following methods were used and compared in anomaly detection modeling: hidden Markov models (HMM), support vector machines (SVM), isolation forest (IF), and reconstruction autoencoders (AEC). They were trained exclusively on sensor signals of the intact state of structures commonly used in various industries, like aerospace and automotive. The signals obtained on artificially introduced damage states were used for performance evaluation. Anomaly assessment was evaluated and compared using various classifiers and feature analysis methods. We introduced novel methodologies for two processes. The first was the dataset preparation with anomalies. The second was the detection and damage severity assessment utilizing the intact object state exclusively. The experiments proved that robust anomaly detection is practically feasible. We were able to train accurate classifiers which had a considerable safety margin. Precise quantitative analysis of damage severity will also be possible when calibration data become available during exploitation or by using expert knowledge.}, language = {en} } @misc{KraljevskiBissiriDuckhornetal., author = {Kraljevski, Ivan and Bissiri, Maria Paola and Duckhorn, Frank and Tsch{\"o}pe, Constanze and Wolff, Matthias}, title = {Glottal Stops in Upper Sorbian: A Data-Driven Approach}, series = {Proc. Interspeech 2021, 30 August - 3 September, 2021, Brno, Czechia}, journal = {Proc. Interspeech 2021, 30 August - 3 September, 2021, Brno, Czechia}, doi = {10.21437/Interspeech.2021-1101}, pages = {1001 -- 1005}, abstract = {We present a data-driven approach for the quantitative analysis of glottal stops before word-initial vowels in Upper Sorbian, a West Slavic minority language spoken in Germany. Glottal stops are word-boundary markers and their detection can improve the performance of automatic speech recognition and speech synthesis systems. We employed cross-language transfer using an acoustic model in German to develop a forced-alignment method for the phonetic segmentation of a read-speech corpus in Upper Sorbian. The missing phonemic units were created by combining the existing phoneme models. In the forced-alignment procedure, the glottal stops were considered optional in front of word-initial vowels. To investigate the influence of speaker type (males, females, and children) and vowel on the occurrence of glottal stops, binomial regression analysis with a generalized linear mixed model was performed. Results show that children glottalize word-initial vowels more frequently than adults, and that glottal stop occurrences are influenced by vowel quality.}, language = {en} } @misc{KraljevskiDuckhornBarthetal., author = {Kraljevski, Ivan and Duckhorn, Frank and Barth, Martin and Tsch{\"o}pe, Constanze and Schubert, Frank and Wolff, Matthias}, title = {Autoencoder-based Ultrasonic NDT of Adhesive Bonds}, series = {IEEE SENSORS 2021, Conference Proceedings, Oct 31- Nov 4, Sydney, Australia}, journal = {IEEE SENSORS 2021, Conference Proceedings, Oct 31- Nov 4, Sydney, Australia}, publisher = {IEEE}, isbn = {978-1-7281-9501-8}, doi = {10.1109/SENSORS47087.2021.9639864}, pages = {4}, abstract = {We present an approach for ultrasonic non-destructive testing of adhesive bonding employing unsupervised machine learning with autoencoders.The models are trained exclusively on the features derived from pulse-echo ultrasonic signals on a specimen with good adhesive bonding and tested on another specimen with artificially added defects.The resulting pseudo-probabilities indicating anomalies are visualized and presented along to the C-scan of the same specimen. As a result, we achieved improved representation of the defects, allowing their automatic and reliable detection.}, language = {en} } @misc{KraljevskiDuckhornTschoepeetal., author = {Kraljevski, Ivan and Duckhorn, Frank and Tsch{\"o}pe, Constanze and Wolff, Matthias}, title = {Convolutional Autoencoders for Health Indicators Extraction in Piezoelectric Sensors}, series = {2020 IEEE Sensors, 25-28 Oct. 2020, Rotterdam, Netherlands,}, journal = {2020 IEEE Sensors, 25-28 Oct. 2020, Rotterdam, Netherlands,}, address = {Rotterdam, Netherlands}, isbn = {978-1-7281-6801-2}, doi = {10.1109/SENSORS47125.2020.9323023}, pages = {1 -- 4}, abstract = {We present a method for extracting health indicators from piezoelectric sensors applied in the case of microfluidic valves. Convolutional autoencoders were used to train a model on the normal operating conditions and tested on signals of different valves. The results of the model performance evaluation, as well as, the qualitative presentation of the indicator plots for each tested component, showed that the used approach is capable of detecting features that correspond to increasing component degradation. The extracted health indicators are the prerequisite and input for reliable remaining useful life prediction.}, language = {en} } @misc{KlimczakKuscheTschoepeetal., author = {Klimczak, Peter and Kusche, Isabel and Tsch{\"o}pe, Constanze and Wolff, Matthias}, title = {Menschliche und maschinelle Entscheidungsrationalit{\"a}t - Zur Kontrolle und Akzeptanz K{\"u}nstlicher Intelligenz}, series = {Zeitschrift f{\"u}r Medienwissenschaft 21 - K{\"u}nstliche Intelligenz}, journal = {Zeitschrift f{\"u}r Medienwissenschaft 21 - K{\"u}nstliche Intelligenz}, number = {2}, isbn = {978-3-8376-4468-5}, issn = {1869-1722}, doi = {/10.25969/mediarep/12631}, pages = {39 -- 45}, language = {de} } @incollection{KraljevskiTschoepeWolff, author = {Kraljevski, Ivan and Tsch{\"o}pe, Constanze and Wolff, Matthias}, title = {Limits and Prospects of Big Data and Small Data Approaches in AI Applications}, series = {AI - Limits and Prospects of Artificial Intelligence}, booktitle = {AI - Limits and Prospects of Artificial Intelligence}, editor = {Klimczak, Peter and Petersen, Christer}, publisher = {transcript Verlag}, address = {Bielefeld}, isbn = {978-3-8376-5732-6}, doi = {10.14361/9783839457320-006}, pages = {115 -- 142}, abstract = {The renaissance of artificial intelligence (AI) in the last decade can be credited to several factors, but chief among these is the ever-increasing availability and miniaturization of computational resources. This process has contributed to the rise of ubiquitous computing via popularizing smart devices and the Internet of Things in everyday life. In turn, this has resulted in the generation of increasingly enormous amounts of data. The tech giants are harvesting and storing data on their clients' behavior and, at the same time, introducing concerns about data privacy and protection. Suddenly, such an abundance of data and computing power, which was unimaginable a few decades ago, has caused a revival of old and the invention of new machine learning paradigms, like Deep Learning. Artificial intelligence has undergone a technological breakthrough in various fields, achieving better than human performance in many areas (such as vision, board games etc.). More complex tasks require more sophisticated algorithms that need more and more data. It has often been said that data is becoming a resource that is "more valuable than oil"; however, not all data is equally available and obtainable. Big data can be described by using the "four Vs"; data with immense velocity, volume, variety, and low veracity. In contrast, small data do not possess any of those qualities; they are limited in size and nature and are observed or produced in a controlled manner. Big data, along with powerful computing and storage resources, allow "black box" AI algorithms for various problems previously deemed unsolvable. One could create AI applications even without the underlying expert knowledge, assuming there are enough data and the right tools available (e.g. end-to-end speech recognition and generation, image and object recognition). There are numerous fields in science, industry and everyday life where AI has vast potential. However, due to the lack of big data, application is not straightforward or even possible. A good example is AI in medicine, where an AI system is intended to assist physicians in diagnosing and treating rare or previously never observed conditions, and there is no or an insufficient amount of data for reliable AI deployment. Both big and small data concepts have limitations and prospects for different fields of application. This paper will try to identify and present them by giving real-world examples in various AI fields.}, language = {en} } @misc{UhligAlkhasliSchubertetal., author = {Uhlig, Sebastian and Alkhasli, Ilkin and Schubert, Frank and Tsch{\"o}pe, Constanze and Wolff, Matthias}, title = {A Review of Synthetic and Augmented Training Data for Machine Learning in Ultrasonic Non-Destructive Evaluation}, series = {Ultrasonics}, journal = {Ultrasonics}, number = {134}, issn = {1874-9968}, doi = {10.1016/j.ultras.2023.107041}, abstract = {Ultrasonic Testing (UT) has seen increasing application of machine learning (ML) in recent years, promoting higher-level automation and decision-making in flaw detection and classification. Building a generalized training dataset to apply ML in non-destructive evaluation (NDE), and thus UT, is exceptionally difficult since data on pristine and representative flawed specimens are needed. Yet, in most UT test cases flawed specimen data is inherently rare making data coverage the leading problem when applying ML. Common data augmentation (DA) strategies offer limited solutions as they don't increase the dataset variance, which can lead to overfitting of the training data. The virtual defect method and the recent application of generative adversarial neural networks (GANs) in UT are sophisticated DA methods targeting to solve this problem. On the other hand, well-established research in modeling ultrasonic wave propagations allows for the generation of synthetic UT training data. In this context, we present a first thematic review to summarize the progress of the last decades on synthetic and augmented UT training data in NDE. Additionally, an overview of methods for synthetic UT data generation and augmentation is presented. Among numerical methods such as finite element, finite difference, and elastodynamic finite integration methods, semi-analytical methods such as general point source synthesis, superposition of Gaussian beams, and the pencil method as well as other UT modeling software are presented and discussed. Likewise, existing DA methods for one- and multidimensional UT data, feature space augmentation, and GANs for augmentation are presented and discussed. The paper closes with an in-detail discussion of the advantages and limitations of existing methods for both synthetic UT training data generation and DA of UT data to aid the decision-making of the reader for the application to specific test cases.}, language = {en} } @misc{MaierKuhnDuckhornetal., author = {Maier, Isidor Konrad and Kuhn, Johannes Ferdinand Joachim and Duckhorn, Frank and Kraljevski, Ivan and Sobe, Daniel and Wolff, Matthias and Tsch{\"o}pe, Constanze}, title = {Word Class Based Language Modeling: A Case of Upper Sorbian}, series = {Proceedings of The Workshop on Resources and Technologies for Indigenous, Endangered and Lesser-resourced Languages in Eurasia within the 13th Language Resources and Evaluation Conference, Marseille, France}, journal = {Proceedings of The Workshop on Resources and Technologies for Indigenous, Endangered and Lesser-resourced Languages in Eurasia within the 13th Language Resources and Evaluation Conference, Marseille, France}, publisher = {European Language Resources Association}, isbn = {978-2-493814-07-4}, pages = {28 -- 35}, abstract = {In this paper we show how word class based language modeling can support the integration of a small language in modern applications of speech technology. The methods described in this paper can be applied for any language. We demonstrate the methods on Upper Sorbian. The word classes model the semantic expressions of numerals, date and time of day. The implementation of the created grammars was realized in the form of finite-state-transducers (FSTs) and minimalists grammars (MGs). We practically demonstrate the usage of the FSTs in a simple smart-home speech application, that is able to set wake-up alarms and appointments expressed in a variety of spontaneous and natural sentences. While the created MGs are not integrated in an application for practical use yet, they provide evidence that MGs could potentially work more efficient than FSTs in built-on applications. In particular, MGs can work with a significantly smaller lexicon size, since their more complex structure lets them generate more expressions with less items, while still avoiding wrong expressions.}, language = {en} } @misc{KraljevskiJuIvanovetal., author = {Kraljevski, Ivan and Ju, Yong Chul and Ivanov, Dmitrij and Tsch{\"o}pe, Constanze and Wolff, Matthias}, title = {How to Do Machine Learning with Small Data? - A Review from an Industrial Perspective}, series = {arXiv}, journal = {arXiv}, abstract = {Artificial intelligence experienced a technological breakthrough in science, industry, and everyday life in the recent few decades. The advancements can be credited to the ever-increasing availability and miniaturization of computational resources that resulted in exponential data growth. However, because of the insufficient amount of data in some cases, employing machine learning in solving complex tasks is not straightforward or even possible. As a result, machine learning with small data experiences rising importance in data science and application in several fields. The authors focus on interpreting the general term of "small data" and their engineering and industrial application role. They give a brief overview of the most important industrial applications of machine learning and small data. Small data is defined in terms of various characteristics compared to big data, and a machine learning formalism was introduced. Five critical challenges of machine learning with small data in industrial applications are presented: unlabeled data, imbalanced data, missing data, insufficient data, and rare events. Based on those definitions, an overview of the considerations in domain representation and data acquisition is given along with a taxonomy of machine learning approaches in the context of small data.}, language = {en} } @misc{KraljevskiDuckhornTschoepeetal., author = {Kraljevski, Ivan and Duckhorn, Frank and Tsch{\"o}pe, Constanze and Schubert, Frank and Wolff, Matthias}, title = {Paper Tissue Softness Rating by Acoustic Emission Analysis}, series = {Applied Sciences}, volume = {13}, journal = {Applied Sciences}, number = {3}, issn = {2076-3417}, doi = {10.3390/app13031670}, abstract = {Softness is one of the essential properties of hygiene tissue products. Reliably measuring it is of utmost importance to ensure the balance between customer expectations and cost-effective tissue production. This study presents a method for assessing softness by analyzing acoustic emissions produced while tearing a tissue specimen. The aim was to train neural network models using the corrected results of human panel tests as the ground truth labels and to predict the tissue softness in two- and three-class recognition tasks. We also investigate the possibility of predicting some production parameters related to the softness property. The results proved that tissue softness and production parameters could be reliably estimated only by the tearing noise.}, language = {en} } @misc{JuKraljevskiNeunuebeletal., author = {Ju, Yong Chul and Kraljevski, Ivan and Neun{\"u}bel, Heiko and Tsch{\"o}pe, Constanze and Wolff, Matthias}, title = {Acoustic Resonance Testing of Small Data on Sintered Cogwheels}, series = {Sensors}, volume = {22}, journal = {Sensors}, number = {15}, issn = {1424-8220}, doi = {10.3390/s22155814}, abstract = {Based on the fact that cogwheels are indispensable parts in manufacturing, we present the acoustic resonance testing (ART) of small data on sintered cogwheels for quality control in the context of non-destructive testing (NDT). Considering the lack of extensive studies on cogwheel data by means of ART in combination with machine learning (ML), we utilize time-frequency domain feature analysis and apply ML algorithms to the obtained feature sets in order to detect damaged samples in two ways: one-class and binary classification. In each case, despite small data, our approach delivers robust performance: All damaged test samples reflecting real-world scenarios are recognized in two one-class classifiers (also called detectors), and one intact test sample is misclassified in binary ones. This shows the usefulness of ML and time-frequency domain feature analysis in ART on a sintered cogwheel dataset.}, language = {en} } @misc{MaierKuhnDuckhornetal., author = {Maier, Isidor Konrad and Kuhn, Johannes and Duckhorn, Frank and Kraljevski, Ivan and Sobe, Daniel and Wolff, Matthias and Tsch{\"o}pe, Constanze}, title = {Word Class Based Language Modeling: A Case of Upper Sorbian, LREC 2022, Marseille}, series = {Language Resources and Evaluation Conference 2022 (LREC 2022), Marseille, 2022-06-13}, journal = {Language Resources and Evaluation Conference 2022 (LREC 2022), Marseille, 2022-06-13}, doi = {10.5281/zenodo.7501145}, pages = {1}, language = {en} } @book{WirschingSchmittWolff, author = {Wirsching, G{\"u}nther and Schmitt, Ingo and Wolff, Matthias}, title = {Quantenlogik, Band 1 : eine Einf{\"u}hrung f{\"u}r Ingenieure und Informatiker}, edition = {2. Auflage}, publisher = {Springer Vieweg}, address = {Berlin ; Heidelberg}, isbn = {978-3-662-71335-8}, doi = {10.1007/978-3-662-71335-8}, pages = {xiii, 495}, abstract = {Messungen an Quantenobjekten haben eine logische Struktur. Diese schließt die klassische Logik ein, geht jedoch weit dar{\"u}ber hinaus. Das wesentliche Ziel dieses Lehrbuchs ist es, die mathematischen Werkzeuge der Quantenlogik zu vermitteln und technische Anwendungsm{\"o}glichkeiten aufzuzeigen. Die daf{\"u}r erforderlichen mathematischen Sachverhalte werden anhand von Beispielen so erl{\"a}utert und motiviert, dass sie f{\"u}r angehende Ingenieure und Informatiker verst{\"a}ndlich sind. Die vorliegende Auflage wurde korrigiert und um zahlreiche Anwendungen, zus{\"a}tzliche Beispiele und Beweise erweitert sowie um ein neues Beispiel zur Mustererkennung erg{\"a}nzt.}, language = {de} } @book{WirschingWolffSchmitt, author = {Wirsching, G{\"u}nther and Wolff, Matthias and Schmitt, Ingo}, title = {Quantenlogik : eine Einf{\"u}hrung f{\"u}r Ingenieure und Informatiker}, edition = {1. Auflage}, publisher = {Springer Vieweg}, address = {Berlin ; Heidelberg}, isbn = {978-3-662-66779-8}, doi = {10.1007/978-3-662-66780-4}, pages = {XI, 386}, abstract = {Das wesentliche Ziel dieses Lehrbuchs ist es, die mathematischen Werkzeuge zur Modellierung kognitiver Strukturen und Prozesse auf der Grundlage der klassischen Logik und der Quantenlogik zu entwickeln. Die daf{\"u}r erforderlichen mathematischen Sachverhalte werden so dargestellt und anhand von Beispielen motiviert, dass sie f{\"u}r angehende Ingenieure und Informatiker verst{\"a}ndlich sind. - Kompakte logische Darstellung der mathematischen Werkzeuge zur Modellierung kognitiver Strukturen und Prozesse - Beispiele erl{\"a}utern die Anwendung im Engineering Zielgruppen sind insbesondere Studierende der Ingenieurwissenschaften und der Informatik, aber auch Studierende der Mathematik oder der Physik k{\"o}nnen durch den anwendungsbezogenen Blick ihren Horizont erweitern.}, language = {de} } @misc{RoemerHuberLieblWolff, author = {R{\"o}mer, Ronald and Huber-Liebl, Markus and Wolff, Matthias}, title = {Quantum-inspired representation and querying of semiotic object properties by cognitive agents}, series = {2025 IEEE 16th International Conference on Cognitive Infocommunications (CogInfoCom)}, journal = {2025 IEEE 16th International Conference on Cognitive Infocommunications (CogInfoCom)}, publisher = {IEEE}, address = {Piscataway, NJ}, isbn = {979-8-3503-5691-5}, doi = {10.1109/CogInfoCom66819.2025.11200567}, pages = {000129 -- 000134}, abstract = {Advanced intelligence often relies on the ability to build and use models. They allow the representation of knowledge, enable predictions, and serve to plan goal-directed actions. However, the successfull use of models requires a certain level of competence in interacting with models. This competence can be acquired by exploiting the separation of the cognitive agent from the objects represented in the model; because it allows the differentiation of individual semiotic levels. This includes the separation of self-sufficient and non self-sufficient object attributes. Non self-sufficient attributes that the agent assigned to potential target objects during the exploration phase form the starting point for the information requirement regarding the self-sufficient attributes of these objects. These attributes are required for target selection and the subsequent alignment of the model-based planning. This process is characterized by a series of queries to the environment model and thus shows a certain similarity to information retrieval (IR). Therefore, in this work we particularly investigate quantum-inspired IR-methods for representation and querying. We demonstrate that they are suitable for modelling cognitive effort and behavior, as they represent a realistic and universally applicable descriptive tool.}, language = {en} } @misc{HuberLieblRosenowRoemeretal., author = {Huber-Liebl, Markus and Rosenow, Tillmann and R{\"o}mer, Ronald and Wirsching, G{\"u}nther and Wolff, Matthias}, title = {Knowledge representation and querying with tensors for a class of practical test problems}, series = {Refereed Paper Proceedings - KM Conference 2025 - Siena, Italy}, journal = {Refereed Paper Proceedings - KM Conference 2025 - Siena, Italy}, publisher = {International Institute for Applied Knowledge Management}, pages = {111 -- 123}, abstract = {We further promote the idea of quantum inspiration and propose to equip cognitive systems not only with tensors for data representation but also for operation representation and querying. We discuss ideas from information retrieval and translate them into our method of behavioral control. We formalize the method with tensor algebra and discuss its extensions to learning. At the example of the problem of 𝑁-dimensional aiming, we visualize the transfer of our stated theoretical foundation to a class of practical test problems.}, language = {en} } @misc{SchmittSowoidnichGosswamietal., author = {Schmitt, Ingo and Sowoidnich, Kay and Gosswami, Tapashi and Sumpf, Bernd and Maiwald, Martin and Wolff, Matthias}, title = {PCA-based peak feature selection for classification of spectroscopic datasets}, series = {Journal of chemometrics}, volume = {39}, journal = {Journal of chemometrics}, number = {11}, publisher = {John Wiley \& Sons Ltd.}, address = {New York, NY}, issn = {0886-9383}, doi = {10.1002/cem.70074}, pages = {1 -- 14}, abstract = {Reducing feature dimensionality in spectroscopic data is crucial for efficient analysis and classification. Using all available features for classification typically results in an unacceptably high runtime and poor accuracy. Popular feature extraction methods, such as principal component analysis (PCA), linear discriminant analysis (LDA), and autoencoders, reduce feature dimensionality by extracting latent features that can be challenging to interpret. To enable better human interpretation of the classification model, we avoid extraction methods and instead propose applying feature selection methods. In this work, we develop an innovative PCA-based feature selection method for spectroscopic data, providing an essential subset of the original features. As an important advantage, no prior knowledge about the characteristic signals of the respective target substance is required. In this proof-of-concept study, the proposed method is initially characterized using simulated Raman and infrared absorption datasets. From the top five PCA eigenvectors of spectroscopic data, we identify a set of three top peaks each at specific wavenumbers (features). The compact set of selected features is then used for classification tasks applying a decision tree. Based on two well-defined spectroscopic datasets, our study demonstrates that our new method of PCA-based peak finding outperforms selected other approaches with regard to interpretability and accuracy. For both investigated datasets, accuracies greater than 97\% are achieved. Our approach shows large potential for accurate classification combined with interpretability in further scenarios involving spectroscopic datasets.}, language = {en} }