TY - CHAP A1 - Ghahremani, Pegah A1 - BabaAli, Bagher A1 - Povey, Daniel A1 - Riedhammer, Korbinian A1 - Trmal, Jan A1 - Khudanpur, Sanjeev T1 - A Pitch Extraction Algorithm Tuned for Automatic Speech Recognition T2 - 2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Florence, Italy, May 2014. N2 - In this paper we present an algorithm that produces pitch and probability-of-voicing estimates for use as features in automatic speech recognition systems. These features give large performance improvements on tonal languages for ASR systems, and even substantial improvements for non-tonal languages. Our method, which we are calling the Kaldi pitch tracker (because we are adding it to the Kaldi ASR toolkit), is a highly modified version of the getf0 (RAPT) algorithm. Unlike the original getf0 we do not make a hard decision whether any given frame is voiced or unvoiced; instead, we assign a pitch even to unvoiced frames while constraining the pitch trajectory to be continuous. Our algorithm also produces a quantity that can be used as a probability of voicing measure; it is based on the normalized autocorrelation measure that our pitch extractor uses. We present results on data from various languages in the BABEL project, and show a large improvement over systems without tonal features and systems where pitch and POV information was obtained from SAcC or getf0. KW - Automatic Speech Recognition Y1 - 2014 PB - IEEE ER - TY - CHAP A1 - Haderlein, Tino A1 - Riedhammer, Korbinian A1 - Maier, Andreas A1 - Nöth, Elmar A1 - Toy, Hikmet A1 - Rosanowski, Frank T1 - An Automatic Version of the Post-Laryngectomy Telephone Test T2 - TSD 2007, 10th International Conference on Text, Speech and Dialogue, Proceedings, Pilsen, Czech Republic, September 2007. N2 - 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 naïve 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. KW - Automatic Speech Recognition KW - Mono Poly KW - Total Laryngectomy KW - Speech Recognition System KW - Automatic Evaluation Y1 - 2007 SP - 238 EP - 245 PB - Springer-Verlag ER - TY - CHAP A1 - Nöth, Elmar A1 - Maier, Andreas A1 - Haderlein, Tino A1 - Riedhammer, Korbinian A1 - Rosanowski, Frank A1 - Schuster, Maria T1 - Automatic Evaluation of Pathologic Speech - from Research to Routine Clinical Use T2 - TSD 2007, 10th International Conference on Text, Speech and Dialogue, Pilsen, Czech Republic, September 2007. N2 - 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. KW - Automatic Speech Recognition KW - Pathologic Speech KW - Automatic Evaluation KW - Prosodic Feature KW - Speech Recognizer Y1 - 2007 SP - 294 EP - 301 PB - Springer-Verlag ER -