@inproceedings{RiedhammerRingNoethetal.2012, author = {Riedhammer, Korbinian and Ring, Martin and N{\"o}th, Elmar and Kolb, Daniel}, title = {A Software Kit for Automatic Voice Descrambling}, series = {2012 IEEE International Conference on Communications (ICC); IEEE International Workshop on Security and Forensics in Communication Systems (SFCS).}, booktitle = {2012 IEEE International Conference on Communications (ICC); IEEE International Workshop on Security and Forensics in Communication Systems (SFCS).}, pages = {8349 -- 8353}, year = {2012}, abstract = {Voice scrambling is widely used to add privacy to the radio communication of various authorities - but is also used by criminals to evade prosecution. In this article, we consider various analog voice scrambling techniques such as fixed frequency inversion, splitband inversion and rolling code scramblers. We explain how to break them using automatically extracted measures and scoring algorithms, and evaluate the proposed system using simulated data. While the simple inversion can be easily broken, the more advanced techniques require additional work prior to unsupervised automatization; the presented user interface allows the user to refine the automatic results to obtain a high quality solution.}, language = {en} } @inproceedings{RiedhammerBockletGoshaletal.2012, author = {Riedhammer, Korbinian and Bocklet, Tobias and Goshal, Arnab and Povey, Daniel}, title = {Revisiting Semi-Continuous Hidden Markov Models}, series = {2012 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Kyoto, Japan, March 2012.}, booktitle = {2012 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Kyoto, Japan, March 2012.}, publisher = {IEEE}, pages = {4721 -- 4724}, year = {2012}, abstract = {In the past decade, semi-continuous hidden Markov models (SCHMMs) have not attracted much attention in the speech recognition community. Growing amounts of training data and increasing sophistication of model estimation led to the impression that continuous HMMs are the best choice of acoustic model. However, recent work on recognition of under-resourced languages faces the same old problem of estimating a large number of parameters from limited amounts of transcribed speech. This has led to a renewed interest in methods of reducing the number of parameters while maintaining or extending the modeling capabilities of continuous models. In this work, we compare classic and multiple-codebook semi-continuous models using diagonal and full covariance matrices with continuous HMMs and subspace Gaussian mixture models. Experiments on the RM and WSJ corpora show that while a classical semicontinuous system does not perform as well as a continuous one, multiple-codebook semi-continuous systems can perform better, particular when using full-covariance Gaussians.}, language = {en} } @inproceedings{PoveyHannemannBoulianneetal.2012, author = {Povey, Daniel and Hannemann, Mirko and Boulianne, Gilles and Burget, Luk{\´a}š and Ghoshal, Arnab and Janda, Miloš and Karafi{\´a}t, Martin and Kombrink, Stefan and Motl{\´i}ček, Petr and Qian, Yanmin and Riedhammer, Korbinian and Vesel{\´y}, Karel and Thang Vu, Ngoc}, title = {Generating Exact Lattices in the WFST Framework}, series = {2012 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Kyoto, Japan, May 2012.}, booktitle = {2012 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Kyoto, Japan, May 2012.}, pages = {4213 -- 4216}, year = {2012}, abstract = {We describe a lattice generation method that is exact, i.e. it satisfies all the natural properties we would want from a lattice of alternative transcriptions of an utterance. This method does not introduce substantial overhead above one-best decoding. Our method is most directly applicable when using WFST decoders where the WFST is "fully expanded", i.e. where the arcs correspond to HMM transitions. It outputs lattices that include HMM-state-level alignments as well as word labels. The general idea is to create a state-level lattice during decoding, and to do a special form of determinization that retains only the best-scoring path for each word sequence. This special determinization algorithm is a solution to the following problem: Given a WFST A, compute a WFST B that, for each input-symbol-sequence of A, contains just the lowest-cost path through A.}, language = {en} } @inproceedings{RiedhammerGroppNoeth2011, author = {Riedhammer, Korbinian and Gropp, Martin and N{\"o}th, Elmar}, title = {A Novel Lecture Browser Using Key Phrases and Stream Graphs}, series = {Lehrstuhl f{\"u}r Mustererkennung, Universit{\"a}t Erlangen-N{\"u}rnberg}, booktitle = {Lehrstuhl f{\"u}r Mustererkennung, Universit{\"a}t Erlangen-N{\"u}rnberg}, year = {2011}, abstract = {We present a novel lecture browser that utilizes ranked key phrases displayed on a stream graph to overcome the shortcomings of traditional extractive (query-based) summaries. The system extracts key phrases from the ASR transcripts, performs an unsupervised ranking, and displays an initial number of phrases on the stream graph. This graph gives an intuition of when which key phrase is spoken, and how dominant it is throughout the lecture. The user can select the phrases to be displayed and furthermore adjust the ranking of the all phrases. All user interactions are logged to a server to improve the ranking algorithms and provide user specific rankings.}, language = {en} } @inproceedings{GroppNoethRiedhammer2011, author = {Gropp, Martin and N{\"o}th, Elmar and Riedhammer, Korbinian}, title = {A Novel Lecture Browsing System Using Ranked Key Phrases and StreamGraphs}, series = {14th International Conference on Text, Speech and Dialogue (TSD), September 2011, Pilsen, Czech Republic.}, booktitle = {14th International Conference on Text, Speech and Dialogue (TSD), September 2011, Pilsen, Czech Republic.}, pages = {17 -- 24}, year = {2011}, abstract = {A growing number of universities offer recordings of lectures, seminars and talks in an online e-learning portal. However, the user is often not interested in the entire recording, but is looking for parts covering a certain topic. Usually, the user has to either watch the whole video or "zap" through the lecture and risk missing important details. We present an integrated web-based platform to help users find relevant sections within recorded lecture videos by providing them with a ranked list of key phrases. For a user-defined subset of these, a StreamGraph visualizes when important key phrases occur and how prominent they are at the given time. To come up with the best key phrase rankings, we evaluate three different key phrase ranking methods using lectures of different topics by comparing automatic with human rankings, and show that human and automatic rankings yield similar scores using Normalized Discounted Cumulative Gain (NDCG).}, language = {en} } @inproceedings{SteidlRiedhammerBockletetal.2011, author = {Steidl, Stefan and Riedhammer, Korbinian and Bocklet, Tobias and H{\"o}nig, Florian and N{\"o}th, Elmar}, title = {Java Visual Speech Components for Rapid Application Development of GUI based Speech Processing Applications}, series = {INTERSPEECH 2011, 12th Annual Conference of the International Speech Communication Association, Florence, Italy, August 2011.}, booktitle = {INTERSPEECH 2011, 12th Annual Conference of the International Speech Communication Association, Florence, Italy, August 2011.}, pages = {3257 -- 3260}, year = {2011}, abstract = {In this paper, we describe a new Java framework for an easy and efficient way of developing new GUI based speech processing applications. Standard components are provided to display the speech signal, the power plot, and the spectrogram. Furthermore, a component to create a new transcription and to display and manipulate an existing transcription is provided, as well as a component to display and manually correct external pitch values. These Swing components can be easily embedded into own Java programs. They can be synchronized to display the same region of the speech file. The object-oriented design provides base classes for rapid development of own components.}, language = {en} } @inproceedings{BockletRiedhammerNoeth2011, author = {Bocklet, Tobias and Riedhammer, Korbinian and N{\"o}th, Elmar}, title = {Drink and Speak: On the automatic classification of alcohol intoxination by acoustic, prosodic and text-based features}, series = {INTERSPEECH 2011, 12th Annual Conference of the International Speech Communication Association, Florence, Italy, August 2011.}, booktitle = {INTERSPEECH 2011, 12th Annual Conference of the International Speech Communication Association, Florence, Italy, August 2011.}, pages = {3213 -- 3216}, year = {2011}, abstract = {This paper focuses on the automatic detection of a person's blood level alcohol based on automatic speech processing approaches. We compare 5 different feature types with different ways of modeling. Experiments are based on the ALC corpus of IS2011 Speaker State Challenge. The classification task is restricted to the detection of a blood alcohol level above 0.5 per mille. Three feature sets are based on spectral observations: MFCCs, PLPs, TRAPS. These are modeled by GMMs. Classification is either done by a Gaussian classifier or by SVMs. In the later case classification is based on GMM-based supervectors, i.e. concatenation of GMM mean vectors. A prosodic system extracts a 292-dimensional feature vector based on a voiced-unvoiced decision. A transcription-based system makes use of text transcriptions related to phoneme durations and textual structure. We compare the stand-alone performances of these systems and combine them on score level by logistic regression. The best stand-alone performance is the transcriptionbased system which outperforms the baseline by 4.8\% on the development set. A Combination on score level gave a huge boost when the spectral-based systems were added (73.6\%). This is a relative improvement of 12.7\% to the baseline. On the test-set we achieved an UA of 68.6\% which is a significant improvement of 4.1\% to the baseline system.}, language = {en} } @inproceedings{RiedhammerBockletNoeth2011, author = {Riedhammer, Korbinian and Bocklet, Tobias and N{\"o}th, Elmar}, title = {Compensation of Extrinsic Variability in Speaker Verification Systems on Simulated Skype and HF Channel Data}, series = {2011 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Prague, Czech Republic, May 2011.}, booktitle = {2011 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Prague, Czech Republic, May 2011.}, pages = {4840 -- 4843}, year = {2011}, abstract = {In this work we focus on speaker verification on channels of varying quality, namely Skype and high frequency (HF) radio. In our setup, we assume to have telephone recordings of speakers for training, but recordings of different channels for testing with varying (lower) signal quality. Starting from a Gaussian mixture / support vector machine (GMM/SVM) baseline, we evaluate multi-condition training (MCT), an ideal channel classification approach (ICC), and nuisance attribute projection (NAP) to compensate for the loss of information due to the transmission. In an evaluation on Switchboard-2 data using Skype and HF channel simulators, we show that, for good signal quality, NAP improves the baseline system performance from 5\% EER to 3.33\% EER (for both Skype and HF). For strongly distorted data, MCT or, if adequate, ICC turn out to be the method of choice.}, language = {en} } @inproceedings{KiesmuellerSossallaBrindaetal.2010, author = {Kiesm{\"u}ller, Ulrich and Sossalla, Sebastian and Brinda, Torsten and Riedhammer, Korbinian}, title = {Online Identification of Learner Problem Solving Strategies Using Pattern Recognition Methods}, series = {Proceedings of the 15th Annual Conference on Innovation and Technology in Computer Science Education (ITiCSE 2010), Bilkent, Ankara, Turkey, June 2010.}, booktitle = {Proceedings of the 15th Annual Conference on Innovation and Technology in Computer Science Education (ITiCSE 2010), Bilkent, Ankara, Turkey, June 2010.}, pages = {274 -- 278}, year = {2010}, abstract = {Learning and programming environments used in computer science education give feedback to the users by system messages. These are triggered by programming errors and give only "technical" hints without regard to the learners' problem solving process. To adapt the messages not only to the factual but also to the procedural knowledge of the learners, their problem solving strategies have to be identified automatically and in process. This article describes a way to achieve this with the help of pattern recognition methods. Using data from a study with 65 learners aged 12 to 13 using a learning environment for programming, a classification system based on hidden Markov models is trained and integrated in the very same environment. We discuss findings in that data and the performance of the automatic online identification, and present first results using the developed software in class.}, language = {en} } @inproceedings{ZaehRiedhammerBockletetal.2010, author = {Z{\"a}h, Uwe and Riedhammer, Korbinian and Bocklet, Tobias and N{\"o}th, Elmar}, title = {Clap Your Hands! Calibrating Spectral Subtraction for Dereverberation}, series = {2010 IEEE International Conference on Acoustics, Speech and Signal Processing(ICASSP), Dallas, TX, USA, March 2010.}, booktitle = {2010 IEEE International Conference on Acoustics, Speech and Signal Processing(ICASSP), Dallas, TX, USA, March 2010.}, pages = {4226 -- 4229}, year = {2010}, abstract = {Reverberation effects as observed by room microphones severely degrade the performance of automatic speech recognition systems. We investigate the use of dereverberation by spectral subtraction as proposed by Lebart and Boucher and introduce a simple approach to estimate the required decay parameter by clapping hands. Experiments on small vocabulary continuous speech recognition task on read speech show that using the calibrated dereverberation improves WER from 73.2 to 54.7 for the best microphone. In combination with system adaptation, the WER could be reduced to 28.2, which is only a 16\% relative loss of performance comparison to using a headset instead of a room microphone.}, language = {en} } @inproceedings{SpieglRiedhammerSteidletal.2010, author = {Spiegl, Werner and Riedhammer, Korbinian and Steidl, Stefan and N{\"o}th, Elmar}, title = {FAU IISAH Corpus - A German Speech Database Consisting of Human-Machine and Human-Human Interaction Acquired by Close-Talking and Far-Distance Microphones}, series = {7th Conference on International Language Resources and Evaluation (LREC 2010), European Language Resources Association (ELRA), Valletta, Malta, May 2010.}, booktitle = {7th Conference on International Language Resources and Evaluation (LREC 2010), European Language Resources Association (ELRA), Valletta, Malta, May 2010.}, pages = {2420 -- 2423}, year = {2010}, language = {en} } @inproceedings{BockletMaierRiedhammeretal.2009, author = {Bocklet, Tobias and Maier, Andreas and Riedhammer, Korbinian and N{\"o}th, Elmar}, title = {Towards a Language-independent Intelligibility Assessment of Children with Cleft Lip and Palate}, series = {WOCCI '09 Proceedings of the 2nd Workshop on Child, Computer and Interaction (WOCCI 2009), Cambridge, Massachusetts, November 2009, Article No. 6.}, booktitle = {WOCCI '09 Proceedings of the 2nd Workshop on Child, Computer and Interaction (WOCCI 2009), Cambridge, Massachusetts, November 2009, Article No. 6.}, organization = {ACM New York, NY, USA ©2009}, pages = {2015 -- 2018}, year = {2009}, abstract = {We describe a novel evaluation system for the intelligibility assessment of children with CLP on standardized tests. The system is solely based on standard cepstral features in form of MFCCs. No other information like word alignments is used. So the system can be easily adapted to other languages. For each child one GMM is created by adaptation of a UBM to the speaker-specific MFCCs. The components of this GMM are concatenated in order to create a so-called GMM supervector. These GMM supervectors are then used as meta features for an SVR. We evaluated our language-independent system on two different datasets of children suffering from CLP. One dataset contains recordings of 35 German children, where the children named different pictograms. The other dataset contains recordings of 14 Italian speaking children, who repeated standardized sentences. On both datasets we achieved high correlations: up to 0.81 for the German dataset and 0.83 for the Italian dataset.}, language = {en} } @inproceedings{FariaRiedhammerJaninetal.2016, author = {Faria, Arlo and Riedhammer, Korbinian and Janin, Adam and Bauer, A.}, title = {REMEETING: Searchable Conversations}, series = {INTERSPEECH 2016, Annual Conference of the International Speech Communication Association (ISCA), IEEE Workshop on Spoken Language Technologies (SLT), San Francisco, USA, September 2016.}, booktitle = {INTERSPEECH 2016, Annual Conference of the International Speech Communication Association (ISCA), IEEE Workshop on Spoken Language Technologies (SLT), San Francisco, USA, September 2016.}, organization = {2016 ISCA}, year = {2016}, language = {en} } @inproceedings{FariaRiedhammer2015, author = {Faria, Arlo and Riedhammer, Korbinian}, title = {REMEETING — Get More Out Of Meetings}, series = {INTERSPEECH 2015, 16th Annual Conference of the International Speech Communication Association, Dresden, Germany, September 2015.}, booktitle = {INTERSPEECH 2015, 16th Annual Conference of the International Speech Communication Association, Dresden, Germany, September 2015.}, year = {2015}, abstract = {Remeeting is a tool that helps you get more out of in-person meetings. Calendar integration and a special email address allow users to email agenda items prior to a certain meeting. A discrete notification at the time of the meeting reminds the user to start the recording. During the meeting, the user focuses on the conversation, or can add notes and photos if desired. After the meeting, every participant gets notified by an automated email that lists the participants along with automatically extracted keywords, notes and photos. This stimulates collaboration, and keeps follow-up contributions at a central place: Just reply to add further notes to the meeting. The resulting meeting "document" can be shared with others and reviewed using a web app that acts as a visual index to the meeting. This makes Remeeting the perfect tool for regular group meetings, standups and interviews, where people typically track progress and follow up on. Remeeting is leveraging, promoting and contributing to open source projects including kaldi and docker.}, language = {en} } @inproceedings{FariaRiedhammer2014, author = {Faria, Arlo and Riedhammer, Korbinian}, title = {REMEETING — Get More Out of Meetings}, series = {INTERSPEECH 2014, 15th Annual Conference of the International Speech Communication Association, IEEE Workshop on Spoken Language Technologies (SLT), Singapore, September 2014.}, booktitle = {INTERSPEECH 2014, 15th Annual Conference of the International Speech Communication Association, IEEE Workshop on Spoken Language Technologies (SLT), Singapore, September 2014.}, year = {2014}, language = {en} } @inproceedings{GargFavreRiedhammeretal.2009, author = {Garg, Nikhil and Favre, Benoit and Riedhammer, Korbinian and Hakkani-T{\"u}r, Dilek}, title = {A Graph Based Method for Meeting Summarization}, series = {INTERSPEECH 2009, 10th Annual Conference of the International Speech Communication Association, Brighton, United Kingdom, September 2009.}, booktitle = {INTERSPEECH 2009, 10th Annual Conference of the International Speech Communication Association, Brighton, United Kingdom, September 2009.}, pages = {1499 -- 1502}, year = {2009}, abstract = {This paper presents an unsupervised, graph based approach for extractive summarization of meetings. Graph based methods such as TextRank have been used for sentence extraction from news articles. These methods model text as a graph with sentences as nodes and edges based on word overlap. A sentence node is then ranked according to its similarity with other nodes. The spontaneous speech in meetings leads to incomplete, informed sentences with high redundancy and calls for additional measures to extract relevant sentences. We propose an extension of the TextRank algorithm that clusters the meeting utterances and uses these clusters to construct the graph. We evaluate this method on the AM I meeting corpus and show a significant improvement over TextRank and other baseline methods.}, language = {en} } @inproceedings{GillickRiedhammerFavreetal.2009, author = {Gillick, Dan and Riedhammer, Korbinian and Favre, Benoit and Hakkani-T{\"u}r, Dilek}, title = {A Global Optimization Framework for Meeting Summarization}, series = {2009 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Taipei, Taiwan, April 2009.}, booktitle = {2009 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Taipei, Taiwan, April 2009.}, pages = {4769 -- 4772}, year = {2009}, abstract = {We introduce a model for extractive meeting summarization based on the hypothesis that utterances convey bits of information, or concepts. Using keyphrases as concepts weighted by frequency, and an integer linear program to determine the best set of utterances, that is, covering as many concepts as possible while satisfying a length constraint, we achieve ROUGE scores at least as good as a ROUGE-based oracle derived from human summaries. This brings us to a critical discussion of ROUGE and the future of extractive meeting summarization.}, language = {en} } @inproceedings{RiedhammerFavreHakkaniTuer2008, author = {Riedhammer, Korbinian and Favre, Benoit and Hakkani-T{\"u}r, Dilek}, title = {A Keyphrase Based Approach to Interactive Meeting Summarization}, series = {2008 IEEE Workshop on Spoken Language Technologies (SLT), Goa, India, December 2008.}, booktitle = {2008 IEEE Workshop on Spoken Language Technologies (SLT), Goa, India, December 2008.}, pages = {153 -- 156}, year = {2008}, abstract = {Rooted in multi-document summarization, maximum marginal relevance (MMR) is a widely used algorithm for meeting summarization (MS). A major problem in extractive MS using MMR is finding a proper query: the centroid based query which is commonly used in the absence of a manually specified query, can not significantly outperform a simple baseline system. We introduce a simple yet robust algorithm to automatically extract keyphrases (KP) from a meeting which can then be used as a query in the MMR algorithm. We show that the KP based system significantly outperforms both baseline and centroid based systems. As human refined KPs show even better summarization performance, we outline how to integrate the KP approach into a graphical user interface allowing interactive summarization to match the user's needs in terms of summary length and topic focus.}, language = {en} } @inproceedings{TurStolckeVossetal.2008, author = {Tur, Gokhan and Stolcke, Andreas and Voss, Lynn and Dowding, John and Favre, Benoit and Fernandez, Raquel and Frampton, Matthew and Frandsen, Michael and Frederickson, Clive and Graciarena, Martin and Hakkani-T{\"u}r, Dilek and Kintzing, Donald and Leveque, Kyle and Mason, Shane and Niekrasz, John and Peters, Stanley and Purver, Matthew and Riedhammer, Korbinian and Shriberg, Elizabeth and Tien, Jing and Vergyri, Dimitra and Yang, Fan}, title = {The CALO Meeting Speech Recognition and Understanding System}, series = {2008 IEEE Workshop on Spoken Language Technologies (SLT), Goa, India, December 2008.}, booktitle = {2008 IEEE Workshop on Spoken Language Technologies (SLT), Goa, India, December 2008.}, pages = {69 -- 72}, year = {2008}, abstract = {The CALO meeting assistant provides for distributed meeting capture, annotation, automatic transcription and semantic analysis of multiparty meetings, and is part of the larger CALO personal assistant system. This paper summarizes the CALO-MA architecture and its speech recognition and understanding components, which include real-time and offline speech transcription, dialog act segmentation and tagging, question-answer pair identification, action item recognition, decision extraction, and summarization.}, language = {en} } @inproceedings{RiedhammerGillickFavreetal.2008, author = {Riedhammer, Korbinian and Gillick, Dan and Favre, Benoit and Hakkani-T{\"u}r, Dilek}, title = {Packing the Meeting Summarization Knapsack}, series = {INTERSPEECH 2008, 9th Annual Conference of the International Speech Communication Association (ISCA), Brisbane, Australia, September 2008.}, booktitle = {INTERSPEECH 2008, 9th Annual Conference of the International Speech Communication Association (ISCA), Brisbane, Australia, September 2008.}, pages = {2434 -- 2437}, year = {2008}, abstract = {Despite considerable work in automatic meeting summarization over the last few years, comparing results remains difficult due to varied task conditions and evaluations. To address this issue, we present a method for determining the best possible extractive summary given an evaluation metric like ROUGE. Our oracle system is based on a knapsack-packing framework, and though NP-Hard, can be solved nearly optimally by a genetic algorithm. To frame new research results in a meaningful context, we suggest presenting our oracle results alongside two simple baselines. We show oracle and baseline results for a variety of evaluation scenarios that have recently appeared in this field.}, language = {en} } @inproceedings{RiedhammerStemmerHaderleinetal.2007, author = {Riedhammer, Korbinian and Stemmer, Georg and Haderlein, Tino and Schuster, Mario and Rosanowski, Frank and N{\"o}th, Elmar and Maier, Andreas}, title = {Towards Robust Automatic Evaluation of Pathologic Telephone Speech}, series = {2007 IEEE Workshop on Automatic Speech Recognition \& Understanding (ASRU), Kyoto, Japan, December 2007.}, booktitle = {2007 IEEE Workshop on Automatic Speech Recognition \& Understanding (ASRU), Kyoto, Japan, December 2007.}, pages = {717 -- 722}, year = {2007}, abstract = {For many aspects of speech therapy an objective evaluation of the intelligibility of a patient's speech is needed. We investigate the evaluation of the intelligibility of speech by means of automatic speech recognition. Previous studies have shown that measures like word accuracy are consistent with human experts' ratings. To ease the patient's burden, it is highly desirable to conduct the assessment via phone. However, the telephone channel influences the quality of the speech signal which negatively affects the results. To reduce inaccuracies, we propose a combination of two speech recognizers. Experiments on two sets of pathological speech show that the combination results in consistent improvements in the correlation between the automatic evaluation and the ratings by human experts. Furthermore, the approach leads to reductions of 10\% and 25\% of the maximum error of the intelligibility measure.}, language = {en} }