@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{GhahremaniBabaAliPoveyetal.2014, author = {Ghahremani, Pegah and BabaAli, Bagher and Povey, Daniel and Riedhammer, Korbinian and Trmal, Jan and Khudanpur, Sanjeev}, title = {A Pitch Extraction Algorithm Tuned for Automatic Speech Recognition}, series = {2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Florence, Italy, May 2014.}, booktitle = {2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Florence, Italy, May 2014.}, publisher = {IEEE}, year = {2014}, abstract = {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.}, 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{WegmannFariaJaninetal.2013, author = {Wegmann, Steven and Faria, Arlo and Janin, Adam and Riedhammer, Korbinian and Morgan, Nelson}, title = {The Tao of ATWV: Probing the mysteries of keyword search performance}, series = {IEEE Workshop on Automatic Speech Recognition and Understanding (ASRU), Olomouc, Czech Republic, Dezember 2013.}, booktitle = {IEEE Workshop on Automatic Speech Recognition and Understanding (ASRU), Olomouc, Czech Republic, Dezember 2013.}, year = {2013}, abstract = {In this paper we apply diagnostic analysis to gain a deeper understanding of the performance of the the keyword search system that we have developed for conversational telephone speech in the IARPA Babel program. We summarize the Babel task, its primary performance metric, "actual term weighted value" (ATWV), and our recognition and keyword search systems. Our analysis uses two new oracle ATWV measures, a bootstrap-based ATWV confidence interval, and includes a study of the underpinnings of the large ATWV gains due to system combination. This analysis quantifies the potential ATWV gains from improving the number of true hits and the overall quality of the detection scores in our system's posting lists. It also shows that system combination improves our systems' ATWV via a small increase in the number of true hits in the posting lists.}, language = {en} }