@inproceedings{RiedhammerBockletOrozcoArroyaveetal.2014, author = {Riedhammer, Korbinian and Bocklet, Tobias and Orozco-Arroyave, Juan Rafael and N{\"o}th, Elmar}, title = {Semi-Automatic Calibration for Dereverberation by Spectral Subtraction for Continuous Speech Recognition}, series = {ITG Symposium on Speech Communication 2014, Erlangen.}, booktitle = {ITG Symposium on Speech Communication 2014, Erlangen.}, publisher = {VDE VERLAG GMBH}, year = {2014}, abstract = {In this article, we describe a semi-automatic calibration algorithm for dereverberation by spectral subtraction. We verify the method by a comparison to a manual calibration derived from measured room impulse responses (RIR). We conduct extensive experiments to understand the effect of all involved parameters and to verify values suggested in the literature. The experiments are performed on a text read by 31 speakers and recorded by a headset and three far-field microphones. Results are measured in terms of automatic speech recognition (ASR) performance using a 1-gram model to emphasize acoustic recognition performance. To accommodate for the acoustic change by dereverberation we apply supervised MAP adaptation to the hidden Markov model output probabilities. The combination of dereverberation and adaptation yields a relative improvement of about 35\% in terms of word error rate (WER) compared to the original signal.}, language = {en} } @inproceedings{BockletMaierRiedhammeretal.2014, author = {Bocklet, Tobias and Maier, Andreas and Riedhammer, Korbinian and Eysholdt, Ulrich and N{\"o}th, Elmar}, title = {Erlangen-CLP: A Large Annotated Corpus of Speech from Children with Cleft Lip and Palate.}, series = {Language Resources and Evaluation Conference (LREC), Reykjavik, Iceland, May 2014.}, booktitle = {Language Resources and Evaluation Conference (LREC), Reykjavik, Iceland, May 2014.}, year = {2014}, abstract = {In this paper we describe Erlangen-CLP, a large speech database of children with Cleft Lip and Palate. More than 800 German children with CLP (most of them between 4 and 18 years old) and 380 age matched control speakers spoke the semi-standardized PLAKSS test that consists of words with all German phonemes in different positions. So far 250 CLP speakers were manually transcribed, 120 of these were analyzed by a speech therapist and 27 of them by four additional therapists. The tharapists marked 6 different processes/criteria like pharyngeal backing and hypernasality which typically occur in speech of people with CLP. We present detailed statistics about the the marked processes and the inter-rater agreement.}, language = {en} } @inproceedings{RiedhammerGroppBockletetal.2013, author = {Riedhammer, Korbinian and Gropp, Martin and Bocklet, Tobias and H{\"o}nig, Florian and N{\"o}th, Elmar and Steidl, Stefan}, title = {LMELectures: A Multimedia Corpus of Academic Spoken English}, series = {First Workshop on Speech, Language and Audio in Multimedia (SLAM 2013), Marseille, France, August 2013, ISCA Archive.}, booktitle = {First Workshop on Speech, Language and Audio in Multimedia (SLAM 2013), Marseille, France, August 2013, ISCA Archive.}, pages = {102 -- 107}, year = {2013}, abstract = {This paper describes the acquisition, transcription and annotation of a multi-media corpus of academic spoken English, the LMELectures. It consists of two lecture se-ries that were read in the summer term 2009 at the com-puter science department of the University of Erlangen-Nuremberg, covering topics in pattern analysis, machine learning and interventional medical image processing. In total, about 40 hours of high-definition audio and video of a single speaker was acquired in a constant recording en-vironment. In addition to the recordings, the presentation slides are available in machine readable (PDF) format. The manual annotations include a suggested segmenta-tion into speech turns and a complete manual transcrip-tion that was done using BLITZSCRIBE2, a new tool for the rapid transcription. For one lecture series, the lecturer assigned key words to each recordings; one recording of that series was further annotated with a list of ranked key phrases by five human annotators each. The corpus is available for non-commercial purpose upon request.}, language = {en} } @inproceedings{BockletRiedhammerEysholdtetal.2013, author = {Bocklet, Tobias and Riedhammer, Korbinian and Eysholdt, Ulrich and N{\"o}th, Elmar}, title = {Automatic Phoneme Analysis in Children with Cleft Lip and Palate}, series = {2013 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Vancouver, BC, Canada, May 2013.}, booktitle = {2013 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Vancouver, BC, Canada, May 2013.}, publisher = {IEEE}, pages = {7572 -- 7576}, year = {2013}, abstract = {Cleft Lip and Palate (CLP) is among the most frequent congenital abnormalities. The impaired facial development affects the articulation, with different phonemes being impacted inhomogeneously among different patients. This work focuses on automatic phoneme analysis of children with CLP for a detailed diagnosis and therapy control. In clinical routine, the state-of-the-art evaluation is based on perceptual evaluations. Perceptual ratings act as ground-truth throughout this work, with the goal to build an automatic system that is as reliable as humans. We propose two different automatic systems focusing on modeling the articulatory space of a speaker: one system models a speaker by a GMM, the other system employs a speech recognition system and estimates fMLLR matrices for each speaker. SVR is then used to predict the perceptual ratings. We show that the fMLLR-based system is able to achieve automatic phoneme evaluation results that are in the same range as perceptual inter-rater-agreements.}, language = {en} } @inproceedings{RiedhammerGroppNoeth2012, author = {Riedhammer, Korbinian and Gropp, Martin and N{\"o}th, Elmar}, title = {The FAU Video Lecture Browser System}, series = {2012 IEEE Spoken Language Technology Workshop (SLT), Miami, FL, USA, December 2012.}, booktitle = {2012 IEEE Spoken Language Technology Workshop (SLT), Miami, FL, USA, December 2012.}, publisher = {IEEE}, pages = {392 -- 397}, year = {2012}, abstract = {A growing number of universities and other educational institutions provide recordings of lectures and seminars as an additional resource to the students. In contrast to educational films that are scripted, directed and often shot by film professionals, these plain recordings are typically not post-processed in an editorial sense. Thus, the videos often contain longer periods of inactivity or silence, unnecessary repetitions, or corrections of prior mistakes. This paper describes the FAU Video Lecture Browser system, a web-based platform for the interactive assessment of video lectures, that helps to close the gap between a plain recording and a useful e-learning resource by displaying automatically extracted and ranked key phrases on an augmented time line based on stream graphs. In a pilot study, users of the interface were able to complete a topic localization task about 29 \% faster than users provided with the video only while achieving about the same accuracy. The user interactions can be logged on the server to collect data to evaluate the quality of the phrases and rankings, and to train systems that produce customized phrase rankings.}, language = {en} } @inproceedings{HoenigBockletRiedhammeretal.2012, author = {H{\"o}nig, Florian and Bocklet, Tobias and Riedhammer, Korbinian and Batliner, Anton and N{\"o}th, Elmar}, title = {The Automatic Assessment of Non-native Prosody: Combining Classical Prosodic Analysis with Acoustic Modelling}, series = {INTERSPEECH 2012, 13th Annual Conference of the International Speech Communication Association (ISCA), Portland, OR, USA, September 2012.}, booktitle = {INTERSPEECH 2012, 13th Annual Conference of the International Speech Communication Association (ISCA), Portland, OR, USA, September 2012.}, year = {2012}, abstract = {In earlier studies, we assessed the degree of non-nativeness employing prosodic information. In this paper, we combine prosodic information with (1) features derived from a Gaussian Mixture Model used as Universal Background Model (GMM-UBM), a powerful approach used in speaker identification, and (2) openSMILE, a standard open-source toolkit for extracting acoustic features. We evaluate our approach with English speech from 94 non-native speakers. GMM-UBM or openSMILE modelling alone yields lower performance than our prosodic feature vector; however, adding information from the GMM-UBM modelling or openSMILE by late fusion improves results.}, language = {en} } @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{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{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{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} } @inproceedings{HaderleinRiedhammerMaieretal.2007, author = {Haderlein, Tino and Riedhammer, Korbinian and Maier, Andreas and N{\"o}th, Elmar and Toy, Hikmet and Rosanowski, Frank}, title = {An Automatic Version of the Post-Laryngectomy Telephone Test}, series = {TSD 2007, 10th International Conference on Text, Speech and Dialogue, Proceedings, Pilsen, Czech Republic, September 2007.}, booktitle = {TSD 2007, 10th International Conference on Text, Speech and Dialogue, Proceedings, Pilsen, Czech Republic, September 2007.}, publisher = {Springer-Verlag}, pages = {238 -- 245}, year = {2007}, abstract = {Tracheoesophageal (TE) speech is a possibility to restore the ability to speak after total laryngectomy, i.e. the removal of the larynx. The quality of the substitute voice has to be evaluated during therapy. For the intelligibility evaluation of German speakers over telephone, the Post-Laryngectomy Telephone Test (PLTT) was defined. Each patient reads out 20 of 400 different monosyllabic words and 5 out of 100 sentences. A human listener writes down the words and sentences understood and computes an overall score. This paper presents a means of objective and automatic evaluation that can replace the subjective method. The scores of 11 na{\"i}ve raters for a set of 31 test speakers were compared to the word recognition rate of speech recognizers. Correlation values of about 0.9 were reached.}, language = {en} } @inproceedings{NoethMaierHaderleinetal.2007, author = {N{\"o}th, Elmar and Maier, Andreas and Haderlein, Tino and Riedhammer, Korbinian and Rosanowski, Frank and Schuster, Maria}, title = {Automatic Evaluation of Pathologic Speech - from Research to Routine Clinical Use}, series = {TSD 2007, 10th International Conference on Text, Speech and Dialogue, Pilsen, Czech Republic, September 2007.}, booktitle = {TSD 2007, 10th International Conference on Text, Speech and Dialogue, Pilsen, Czech Republic, September 2007.}, publisher = {Springer-Verlag}, pages = {294 -- 301}, year = {2007}, abstract = {Previously we have shown that ASR technology can be used to objectively evaluate pathologic speech. Here we report on progress for routine clinical use: 1) We introduce an easy-to-use recording and evaluation environment. 2) We confirm our previous results for a larger group of patients. 3) We show that telephone speech can be analyzed with the same methods with only a small loss of agreement with human experts. 4) We show that prosodic information leads to more robust results. 5) We show that text reference instead of transliteration can be used for evaluation. Using word accuracy of a speech recognizer and prosodic features as features for SVM regression, we achieve a correlation of .90 between the automatic analysis and human experts.}, language = {en} } @inproceedings{HaderleinEysholdtRiedhammeretal.2007, author = {Haderlein, Tino and Eysholdt, Ulrich and Riedhammer, Korbinian and N{\"o}th, Elmar and Rosanowski, Frank}, title = {Automatisierung des Postlaryngektomie-Telefontests (PLTT)}, series = {Aktuelle phoniatrisch-p{\"a}daudiologische Aspekte}, booktitle = {Aktuelle phoniatrisch-p{\"a}daudiologische Aspekte}, pages = {66 -- 69}, year = {2007}, abstract = {In fr{\"u}heren Arbeiten wurde gezeigt, dass automatische Spracherkennungsverfahren verwendet werden k{\"o}nnen, um die Verst{\"a}ndlichkeit von Sprechern mit tracheo{\"o}sophagealer Ersatzstimme (TE-Stimme) automatisch zu bewerten [1,2]. In diesem Beitrag wird eine automatische Version des Postlaryngektomie-Telefontests (PLTT, [3]) vorgestellt, der einen eingef{\"u}hrten Standardtest f{\"u}r die Verst{\"a}ndlichkeit {\"u}ber das Telefon darstellt.}, language = {de} } @inproceedings{RiedhammerHaderleinSchusteretal.2006, author = {Riedhammer, Korbinian and Haderlein, Tino and Schuster, Maria and Rosanowski, Frank and N{\"o}th, Elmar}, title = {Automatic Evaluation of Tracheoesophageal Telephone Speech}, series = {First International Language Technologies Conference (IS-LTC 2006), Ljubljana, Slovenia, October 2006.}, booktitle = {First International Language Technologies Conference (IS-LTC 2006), Ljubljana, Slovenia, October 2006.}, pages = {17 -- 22}, year = {2006}, abstract = {The tracheoesophageal (TE) substitute voice is currently state-of-the-art treatment to restore the ability to speak after laryngectomy. The intelligibility while talking over a telephone is an important clinical factor, as it is a crucial part of the patients' social life. An objective way to rate the intelligibility of substitute voices when talking over a telephone is desirable to improve the post-laryngectomy speech therapy. An automatic speech recognition (ASR) system was applied to 41 high quality recordings of post-laryngectomy patients. The ASR system was trained with normal, non-pathologic speech. It yielded a word accuracy (WA) of 36.9\%±18.0\%; compared to the intelligibility rating of a group of human experts the ASR system had a correlation coefficient of -.88. After downsampling the 41 recordings to telephone quality, the ASR system reached a WA of 26.4\%±13.9\% leading to a correlation coefficient of -.80. These results confirm that an ASR system can be used for objective intelligibility rating over the telephone.}, language = {en} } @inproceedings{RiedhammerHaderleinNoethetal.2006, author = {Riedhammer, Korbinian and Haderlein, Tino and N{\"o}th, Elmar and Toy, Hikmet and Eysholdt, Ulrich and Rosanowski, Frank}, title = {Die tracheo{\"o}sophageale Ersatzstimme: Automatische Verst{\"a}ndlichkeitsbewertung {\"u}ber das Telefon}, series = {23. Wissenschaftliche Jahrestagung der Deutschen Gesellschaft f{\"u}r Phoniatrie und P{\"a}daudiologie. Heidelberg, September 2006. Aktuelle phoniatrisch-p{\"a}daudiologische Aspekte.}, booktitle = {23. Wissenschaftliche Jahrestagung der Deutschen Gesellschaft f{\"u}r Phoniatrie und P{\"a}daudiologie. Heidelberg, September 2006. Aktuelle phoniatrisch-p{\"a}daudiologische Aspekte.}, pages = {51 -- 53}, year = {2006}, abstract = {Die tracheo{\"o}sophageale Ersatzstimme TE ist heute "state of the art" der Stimmrehabilitation nach einer Laryngektomie. In dieser Studie, einem Teilprojekt eines von der Deutschen Krebshilfe gef{\"o}rderten Forschungsvorhabens, ging es um die objektive Bewertung des Behandlungsfortschritts. Untersucht wurden 41 Laryngektomierte mit einer TE (Provox-Stimmventilprothese) durchgef{\"u}hrt. Ziel der Studie war es, die Verst{\"a}ndlichkeit im Gespr{\"a}ch und am Telefon objektiv zu beurteilen und zu vergleichen, um den Patienten in der Zukunft die telefonische Evaluation von zuhause aus zu erm{\"o}glichen. Zur Bewertung diente ein f{\"u}r Marktzwecke professionalisiertes automatisches Spracherkennungssystem. Es wurden zun{\"a}chst Nahbesprechungsaufnahmen des "Nordwind und Sonne"-Textes von f{\"u}nf Experten hinsichtlich ihrer Verst{\"a}ndlichkeit beurteilt. Aus diesen Aufnahmen entstanden durch Abspielen {\"u}ber ein Telefon simulierte Telefonaufnahmen. Zielkriterium der automatischen Analyse war die Wortakkuratheit WA, die mit der an Schulnoten orientierten Stimmbewertung durch die Experten korreliert wurde. Die Studie ergab eine Korrelation von -0,82 f{\"u}r die Nahbesprechungs- und -0,69 f{\"u}r die Telefonaufnahmen. Die Ergebnisse zeigen, dass die automatische Verst{\"a}ndlichkeitsbewertung von Ersatzstimmen auch per Telefon prinzipiell m{\"o}glich ist. M{\"o}glichkeiten, die Qualit{\"a}tsverluste durch die Telefon{\"u}bertragung und die somit niedrigere Korrelation zu kompensieren, werden aufgezeigt.}, language = {de} } @article{HaderleinRiedhammerNoethetal.2008, author = {Haderlein, Tino and Riedhammer, Korbinian and N{\"o}th, Elmar and Toy, Hikmet and Schuster, Maria and Eysholdt, Ulrich and Hornegger, Joachim and Rosanowski, Frank}, title = {Application of Automatic Speech Recognition to Quantitative Assessment of Tracheoesophageal Speech in Different Signal Quality}, series = {Folia Phoniatrica Et Logopaedica}, volume = {2008}, journal = {Folia Phoniatrica Et Logopaedica}, number = {61(1)}, pages = {12 -- 17}, year = {2008}, abstract = {Tracheoesophageal voice is state-of-the-art in voice rehabilitation after laryngectomy. Intelligibility on a telephone is an important evaluation criterion as it is a crucial part of social life. An objective measure of intelligibility when talking on a telephone is desirable in the field of postlaryngectomy speech therapy and its evaluation. Based upon successful earlier studies with broadband speech, an automatic speech recognition (ASR) system was applied to 41 recordings of postlaryngectomy patients. Recordings were available in different signal qualities; quality was the crucial criterion for this study. Compared to the intelligibility rating of 5 human experts, the ASR system had a correlation coefficient of r = -0.87 and Krippendorff's alpha of 0.65 when broadband speech was processed. The rater group alone achieved alpha = 0.66. With the test recordings in telephone quality, the system reached r = -0.79 and alpha = 0.67. For medical purposes, a comprehensive diagnostic approach to (substitute) voice has to cover both subjective and objective tests. An automatic recognition system such as the one proposed in this study can be used for objective intelligibility rating with results comparable to those of human experts. This holds for broadband speech as well as for automatic evaluation via telephone.}, language = {en} } @article{BockletRiedhammerNoethetal.2012, author = {Bocklet, Tobias and Riedhammer, Korbinian and N{\"o}th, Elmar and Eysholdt, Ulrich and Haderlein, Tino}, title = {Automatic Intelligibility Assessment of Speakers After Laryngeal Cancer by Means of Acoustic Modeling}, series = {Journal of Voice}, journal = {Journal of Voice}, number = {26(3)}, pages = {390 -- 397}, year = {2012}, abstract = {One aspect of voice and speech evaluation after laryngeal cancer is acoustic analysis. Perceptual evaluation by expert raters is a standard in the clinical environment for global criteria such as overall quality or intelligibility. So far, automatic approaches evaluate acoustic properties of pathologic voices based on voiced/unvoiced distinction and fundamental frequency analysis of sustained vowels. Because of the high amount of noisy components and the increasing aperiodicity of highly pathologic voices, a fully automatic analysis of fundamental frequency is difficult. We introduce a purely data-driven system for the acoustic analysis of pathologic voices based on recordings of a standard text.}, language = {en} } @article{HaderleinRiedhammerMaieretal.2009, author = {Haderlein, Tino and Riedhammer, Korbinian and Maier, Andreas and N{\"o}th, Elmar and Eysholdt, Ulrich and Rosanowski, Frank}, title = {Automatisierung des Postlaryngektomie-Telefontests}, series = {HNO}, volume = {2009}, journal = {HNO}, number = {57}, publisher = {Springer-Verlag}, pages = {51 -- 56}, year = {2009}, abstract = {In dieser Studie wird ein objektives Verfahren f{\"u}r die Verst{\"a}ndlichkeitsmessung mit dem Postlaryngektomie-Telefontest (PLTT) mittels automatischer Spracherkennungstechnik beschrieben. 31 Sprecher mit tracheo{\"o}sophagealer Ersatzstimme (25 M{\"a}nner und 6 Frauen; 63,4±8,7 Jahre) wurden zun{\"a}chst von 11 naiven H{\"o}rern bewertet. Der vom Spracherkennungssystem ermittelte Verst{\"a}ndlichkeitsgrad wird als Prozentsatz korrekt verstandener W{\"o}rter einer Wortkette, der Wortakkuratheit bzw. -korrektheit, angegeben und mit den subjektiv ermittelten PLTT-Werten verglichen. Die durchschnittliche PLTT-Gesamtverst{\"a}ndlichkeit der 11 naiven H{\"o}rer liegt bei 47\%, die automatisch ermittelte Wortakkuratheit und Wortkorrektheit liegen deutlich niedriger (etwa 0\% bzw. etwa 15\%). Die Korrelation zwischen menschlicher und maschineller Bewertung liegt jedoch z. T. {\"u}ber 0,9. F{\"u}r den Gesamtverst{\"a}ndlichkeitswert des PLTT kann mit Hilfe der automatischen Spracherkennung objektiv und effizient ein {\"a}quivalentes Maß berechnet werden.}, language = {de} }