@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{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{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{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} }