@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{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} } @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} }