Pub Date : 2007-12-01DOI: 10.1109/ASRU.2007.4430110
Keelan Evanini, David Suendermann-Oeft, R. Pieraccini
This paper compares six algorithms for call classification in the framework of a dialog system for automated troubleshooting. The comparison is carried out on large datasets, each consisting of over 100,000 utterances from two domains: television (TV) and Internet (INT). In spite of the high number of classes (79 for TV and 58 for INT), the best classifier (maximum entropy on word bigrams) achieved more than 77% classification accuracy on the TV dataset and 81% on the INT dataset.
{"title":"Call classification for automated troubleshooting on large corpora","authors":"Keelan Evanini, David Suendermann-Oeft, R. Pieraccini","doi":"10.1109/ASRU.2007.4430110","DOIUrl":"https://doi.org/10.1109/ASRU.2007.4430110","url":null,"abstract":"This paper compares six algorithms for call classification in the framework of a dialog system for automated troubleshooting. The comparison is carried out on large datasets, each consisting of over 100,000 utterances from two domains: television (TV) and Internet (INT). In spite of the high number of classes (79 for TV and 58 for INT), the best classifier (maximum entropy on word bigrams) achieved more than 77% classification accuracy on the TV dataset and 81% on the INT dataset.","PeriodicalId":371729,"journal":{"name":"2007 IEEE Workshop on Automatic Speech Recognition & Understanding (ASRU)","volume":"43 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121623531","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2007-12-01DOI: 10.1109/ASRU.2007.4430180
Björn Schuller, Bogdan Vlasenko, Ricardo Minguez, G. Rigoll, A. Wendemuth
In the search for a standard unit for use in recognition of emotion in speech, a whole turn, that is the full section of speech by one person in a conversation, is common. Within applications such turns often seem favorable. Yet, high effectiveness of sub-turn entities is known. In this respect a two-stage approach is investigated to provide higher temporal resolution by chunking of speech-turns according to acoustic properties, and multi-instance learning for turn-mapping after individual chunk analysis. For chunking fast pre-segmentation into emotionally quasi-stationary segments by one-pass Viterbi beam search with token passing basing on MFCC is used. Chunk analysis is realized by brute-force large feature space construction with subsequent subset selection, SVM classification, and speaker normalization. Extensive tests reveal differences compared to one-stage processing. Alternatively, syllables are used for chunking.
{"title":"Comparing one and two-stage acoustic modeling in the recognition of emotion in speech","authors":"Björn Schuller, Bogdan Vlasenko, Ricardo Minguez, G. Rigoll, A. Wendemuth","doi":"10.1109/ASRU.2007.4430180","DOIUrl":"https://doi.org/10.1109/ASRU.2007.4430180","url":null,"abstract":"In the search for a standard unit for use in recognition of emotion in speech, a whole turn, that is the full section of speech by one person in a conversation, is common. Within applications such turns often seem favorable. Yet, high effectiveness of sub-turn entities is known. In this respect a two-stage approach is investigated to provide higher temporal resolution by chunking of speech-turns according to acoustic properties, and multi-instance learning for turn-mapping after individual chunk analysis. For chunking fast pre-segmentation into emotionally quasi-stationary segments by one-pass Viterbi beam search with token passing basing on MFCC is used. Chunk analysis is realized by brute-force large feature space construction with subsequent subset selection, SVM classification, and speaker normalization. Extensive tests reveal differences compared to one-stage processing. Alternatively, syllables are used for chunking.","PeriodicalId":371729,"journal":{"name":"2007 IEEE Workshop on Automatic Speech Recognition & Understanding (ASRU)","volume":"19 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133101078","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2007-12-01DOI: 10.1109/ASRU.2007.4430143
G. Saon, M. Picheny
We describe a cardinal-synchronous Viterbi decoder for statistical phrase-based machine translation which can operate on general ASR lattices (as opposed to confusion networks). The decoder implements constrained source reordering on the input lattice and makes use of an outbound distortion model to score the possible reorderings. The phrase table, representing the decoding search space, is encoded as a weighted finite state acceptor which is determined and minimized. At a high level, the search proceeds by performing simultaneous transitions in two pairs of automata: (input lattice, phrase table FSM) and (phrase table FSM, target language model). An alternative decoding strategy that we explore is to break the search into two independent subproblems: first, we perform monotone lattice decoding and find the best foreign path through the ASR lattice and then, we decode this path with reordering using standard sentence-based SMT. We report experimental results on several testsets of a large scale Arabic-to-English speech translation task in the context of the global autonomous language exploitation (or GALE) DARPA project. The results indicate that, for monotone search, lattice-based decoding outperforms 1-best decoding whereas for search with reordering, only the second decoding strategy was found to be superior to 1-best decoding. In both cases, the improvements hold only for shallow lattices.
{"title":"Lattice-based Viterbi decoding techniques for speech translation","authors":"G. Saon, M. Picheny","doi":"10.1109/ASRU.2007.4430143","DOIUrl":"https://doi.org/10.1109/ASRU.2007.4430143","url":null,"abstract":"We describe a cardinal-synchronous Viterbi decoder for statistical phrase-based machine translation which can operate on general ASR lattices (as opposed to confusion networks). The decoder implements constrained source reordering on the input lattice and makes use of an outbound distortion model to score the possible reorderings. The phrase table, representing the decoding search space, is encoded as a weighted finite state acceptor which is determined and minimized. At a high level, the search proceeds by performing simultaneous transitions in two pairs of automata: (input lattice, phrase table FSM) and (phrase table FSM, target language model). An alternative decoding strategy that we explore is to break the search into two independent subproblems: first, we perform monotone lattice decoding and find the best foreign path through the ASR lattice and then, we decode this path with reordering using standard sentence-based SMT. We report experimental results on several testsets of a large scale Arabic-to-English speech translation task in the context of the global autonomous language exploitation (or GALE) DARPA project. The results indicate that, for monotone search, lattice-based decoding outperforms 1-best decoding whereas for search with reordering, only the second decoding strategy was found to be superior to 1-best decoding. In both cases, the improvements hold only for shallow lattices.","PeriodicalId":371729,"journal":{"name":"2007 IEEE Workshop on Automatic Speech Recognition & Understanding (ASRU)","volume":"102 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133681294","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2007-12-01DOI: 10.1109/ASRU.2007.4430137
A. Ljolje, Vincent Goffin
A barge-in system designed to reflect the design of the acoustic model used in commercial applications has been built and evaluated. It uses standard hidden Markov model structures, cepstral features and multiple hidden Markov models for both the speech and non-speech parts of the model. It is tested on a large number of real-world databases using noisy speech onset positions which were determined by forced alignment of lexical transcriptions with the recognition model. The ML trained model achieves low false rejection rates at the expense of high false acceptance rates. The discriminative training using the modified algorithm based on the maximum mutual information criterion reduces the false acceptance rates by a half, while preserving the low false rejection rates. Combining an energy based voice activity detector with the hidden Markov model based barge-in models achieves the best performance.
{"title":"Discriminative training of multi-state barge-in models","authors":"A. Ljolje, Vincent Goffin","doi":"10.1109/ASRU.2007.4430137","DOIUrl":"https://doi.org/10.1109/ASRU.2007.4430137","url":null,"abstract":"A barge-in system designed to reflect the design of the acoustic model used in commercial applications has been built and evaluated. It uses standard hidden Markov model structures, cepstral features and multiple hidden Markov models for both the speech and non-speech parts of the model. It is tested on a large number of real-world databases using noisy speech onset positions which were determined by forced alignment of lexical transcriptions with the recognition model. The ML trained model achieves low false rejection rates at the expense of high false acceptance rates. The discriminative training using the modified algorithm based on the maximum mutual information criterion reduces the false acceptance rates by a half, while preserving the low false rejection rates. Combining an energy based voice activity detector with the hidden Markov model based barge-in models achieves the best performance.","PeriodicalId":371729,"journal":{"name":"2007 IEEE Workshop on Automatic Speech Recognition & Understanding (ASRU)","volume":"13 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133540383","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2007-12-01DOI: 10.1109/ASRU.2007.4430132
J. Hershey, P. Olsen, Steven J. Rennie
Divergence measures are widely used tools in statistics and pattern recognition. The Kullback-Leibler (KL) divergence between two hidden Markov models (HMMs) would be particularly useful in the fields of speech and image recognition. Whereas the KL divergence is tractable for many distributions, including Gaussians, it is not in general tractable for mixture models or HMMs. Recently, variational approximations have been introduced to efficiently compute the KL divergence and Bhattacharyya divergence between two mixture models, by reducing them to the divergences between the mixture components. Here we generalize these techniques to approach the divergence between HMMs using a recursive backward algorithm. Two such methods are introduced, one of which yields an upper bound on the KL divergence, the other of which yields a recursive closed-form solution. The KL and Bhattacharyya divergences, as well as a weighted edit-distance technique, are evaluated for the task of predicting the confusability of pairs of words.
{"title":"Variational Kullback-Leibler divergence for Hidden Markov models","authors":"J. Hershey, P. Olsen, Steven J. Rennie","doi":"10.1109/ASRU.2007.4430132","DOIUrl":"https://doi.org/10.1109/ASRU.2007.4430132","url":null,"abstract":"Divergence measures are widely used tools in statistics and pattern recognition. The Kullback-Leibler (KL) divergence between two hidden Markov models (HMMs) would be particularly useful in the fields of speech and image recognition. Whereas the KL divergence is tractable for many distributions, including Gaussians, it is not in general tractable for mixture models or HMMs. Recently, variational approximations have been introduced to efficiently compute the KL divergence and Bhattacharyya divergence between two mixture models, by reducing them to the divergences between the mixture components. Here we generalize these techniques to approach the divergence between HMMs using a recursive backward algorithm. Two such methods are introduced, one of which yields an upper bound on the KL divergence, the other of which yields a recursive closed-form solution. The KL and Bhattacharyya divergences, as well as a weighted edit-distance technique, are evaluated for the task of predicting the confusability of pairs of words.","PeriodicalId":371729,"journal":{"name":"2007 IEEE Workshop on Automatic Speech Recognition & Understanding (ASRU)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124385471","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2007-12-01DOI: 10.1109/ASRU.2007.4430194
Scott Otterson, Mari Ostendorf
Speaker overlap in meetings is thought to be a significant contributor to error in speaker diarization, but it is not clear if overlaps are problematic for speaker clustering and/or if errors could be addressed by assigning multiple labels in overlap regions. In this paper, we look at these issues experimentally, assuming perfect detection of overlaps, to assess the relative importance of these problems and the potential impact of overlap detection. With our best features, we find that detecting overlaps could potentially improve diarization accuracy by 15% relative, using a simple strategy of assigning speaker labels in overlap regions according to the labels of the neighboring segments. In addition, the use of cross-correlation features with MFCC's reduces the performance gap due to overlaps, so that there is little gain from removing overlapped regions before clustering.
{"title":"Efficient use of overlap information in speaker diarization","authors":"Scott Otterson, Mari Ostendorf","doi":"10.1109/ASRU.2007.4430194","DOIUrl":"https://doi.org/10.1109/ASRU.2007.4430194","url":null,"abstract":"Speaker overlap in meetings is thought to be a significant contributor to error in speaker diarization, but it is not clear if overlaps are problematic for speaker clustering and/or if errors could be addressed by assigning multiple labels in overlap regions. In this paper, we look at these issues experimentally, assuming perfect detection of overlaps, to assess the relative importance of these problems and the potential impact of overlap detection. With our best features, we find that detecting overlaps could potentially improve diarization accuracy by 15% relative, using a simple strategy of assigning speaker labels in overlap regions according to the labels of the neighboring segments. In addition, the use of cross-correlation features with MFCC's reduces the performance gap due to overlaps, so that there is little gain from removing overlapped regions before clustering.","PeriodicalId":371729,"journal":{"name":"2007 IEEE Workshop on Automatic Speech Recognition & Understanding (ASRU)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123828210","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2007-12-01DOI: 10.1109/ASRU.2007.4430135
K. Schutte, James R. Glass
A method for acoustic modeling of speech is presented which is based on learning and detecting the occurrence of localized time-frequency patterns in a spectrogram. A boosting algorithm is applied to both build classifiers and perform feature selection from a large set of features derived by filtering spectrograms. Initial experiments are performed to discriminate digits in the Aurora database. The system succeeds in learning sequences of localized time-frequency patterns which are highly interpretable from an acoustic-phonetic viewpoint. While the work and the results are preliminary, they suggest that pursuing these techniques further could lead to new approaches to acoustic modeling for ASR which are more noise robust and offer better encoding of temporal dynamics than typical features such as frame-based cepstra.
{"title":"Speech recognition with localized time-frequency pattern detectors","authors":"K. Schutte, James R. Glass","doi":"10.1109/ASRU.2007.4430135","DOIUrl":"https://doi.org/10.1109/ASRU.2007.4430135","url":null,"abstract":"A method for acoustic modeling of speech is presented which is based on learning and detecting the occurrence of localized time-frequency patterns in a spectrogram. A boosting algorithm is applied to both build classifiers and perform feature selection from a large set of features derived by filtering spectrograms. Initial experiments are performed to discriminate digits in the Aurora database. The system succeeds in learning sequences of localized time-frequency patterns which are highly interpretable from an acoustic-phonetic viewpoint. While the work and the results are preliminary, they suggest that pursuing these techniques further could lead to new approaches to acoustic modeling for ASR which are more noise robust and offer better encoding of temporal dynamics than typical features such as frame-based cepstra.","PeriodicalId":371729,"journal":{"name":"2007 IEEE Workshop on Automatic Speech Recognition & Understanding (ASRU)","volume":"36 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114384991","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2007-12-01DOI: 10.1109/ASRU.2007.4430158
B. Ramabhadran, O. Siohan, A. Sethy
TC-STAR is an European Union funded speech to speech translation project to transcribe, translate and synthesize European Parliamentary Plenary Speeches (EPPS). This paper describes IBM's English speech recognition system submitted to the TC-STAR 2007 Evaluation. Language model adaptation based on clustering and data selection using relative entropy minimization provided significant gains in the 2007 evaluation. The additional advances over the 2006 system that we present in this paper include unsupervised training of acoustic and language models; a system architecture that is based on cross-adaptation across complementary systems and system combination through generation of an ensemble of systems using randomized decision tree state-tying. These advances reduced the error rate by 30% relative over the best-performing system in the TC-STAR 2006 evaluation on the 2006 English development and evaluation test sets, and produced one of the best performing systems on the 2007 evaluation in English with a word error rate of 7.1%.
{"title":"The IBM 2007 speech transcription system for European parliamentary speeches","authors":"B. Ramabhadran, O. Siohan, A. Sethy","doi":"10.1109/ASRU.2007.4430158","DOIUrl":"https://doi.org/10.1109/ASRU.2007.4430158","url":null,"abstract":"TC-STAR is an European Union funded speech to speech translation project to transcribe, translate and synthesize European Parliamentary Plenary Speeches (EPPS). This paper describes IBM's English speech recognition system submitted to the TC-STAR 2007 Evaluation. Language model adaptation based on clustering and data selection using relative entropy minimization provided significant gains in the 2007 evaluation. The additional advances over the 2006 system that we present in this paper include unsupervised training of acoustic and language models; a system architecture that is based on cross-adaptation across complementary systems and system combination through generation of an ensemble of systems using randomized decision tree state-tying. These advances reduced the error rate by 30% relative over the best-performing system in the TC-STAR 2006 evaluation on the 2006 English development and evaluation test sets, and produced one of the best performing systems on the 2007 evaluation in English with a word error rate of 7.1%.","PeriodicalId":371729,"journal":{"name":"2007 IEEE Workshop on Automatic Speech Recognition & Understanding (ASRU)","volume":"243 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122719420","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2007-12-01DOI: 10.1109/ASRU.2007.4430093
S. Yamamoto, K. Nakadai, Mikio Nakano, H. Tsujino, J. Valin, Kazunori Komatani, T. Ogata, HIroshi G. Okuno
This paper addresses robot audition that can cope with speech that has a low signal-to-noise ratio (SNR) in real time by using robot-embedded microphones. To cope with such a noise, we exploited two key ideas; Preprocessing consisting of sound source localization and separation with a microphone array, and system integration based on missing feature theory (MFT). Preprocessing improves the SNR of a target sound signal using geometric source separation with multichannel post-filter. MFT uses only reliable acoustic features in speech recognition and masks unreliable parts caused by errors in preprocessing. MFT thus provides smooth integration between preprocessing and automatic speech recognition. A real-time robot audition system based on these two key ideas is constructed for Honda ASIMO and Humanoid SIG2 with 8-ch microphone arrays. The paper also reports the improvement of ASR performance by using two and three simultaneous speech signals.
{"title":"Design and implementation of a robot audition system for automatic speech recognition of simultaneous speech","authors":"S. Yamamoto, K. Nakadai, Mikio Nakano, H. Tsujino, J. Valin, Kazunori Komatani, T. Ogata, HIroshi G. Okuno","doi":"10.1109/ASRU.2007.4430093","DOIUrl":"https://doi.org/10.1109/ASRU.2007.4430093","url":null,"abstract":"This paper addresses robot audition that can cope with speech that has a low signal-to-noise ratio (SNR) in real time by using robot-embedded microphones. To cope with such a noise, we exploited two key ideas; Preprocessing consisting of sound source localization and separation with a microphone array, and system integration based on missing feature theory (MFT). Preprocessing improves the SNR of a target sound signal using geometric source separation with multichannel post-filter. MFT uses only reliable acoustic features in speech recognition and masks unreliable parts caused by errors in preprocessing. MFT thus provides smooth integration between preprocessing and automatic speech recognition. A real-time robot audition system based on these two key ideas is constructed for Honda ASIMO and Humanoid SIG2 with 8-ch microphone arrays. The paper also reports the improvement of ASR performance by using two and three simultaneous speech signals.","PeriodicalId":371729,"journal":{"name":"2007 IEEE Workshop on Automatic Speech Recognition & Understanding (ASRU)","volume":"43 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115259837","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2007-12-01DOI: 10.1109/ASRU.2007.4430083
T. Jitsuhiro, T. Toriyama, K. Kogure
This paper presents robust speech recognition using a noise suppression method based on multi-model compositions and multi-pass search. In real environments, many kinds of noise signals exists, and input speech for speech recognition systems include them. Our task in the E-Nightingale project is speech recognition of voice memoranda spoken by nurses during actual work at hospitals. To obtain good recognized candidates, suppressing many kinds of noise signals at once to find target speech is important. First, before noise suppression, to find speech and noise label sequences, we introduce multi-pass search with acoustic models including many kinds of noise models and their compositions, their n-gram models, and their lexicon. Second, noise suppression based on models is performed using the multiple composite models selected by recognized label sequences with time alignments. We evaluated this approach using the E-Nightingale task, and the proposed method outperformed the conventional method.
{"title":"Robust speech recognition using noise suppression based on multiple composite models and multi-pass search","authors":"T. Jitsuhiro, T. Toriyama, K. Kogure","doi":"10.1109/ASRU.2007.4430083","DOIUrl":"https://doi.org/10.1109/ASRU.2007.4430083","url":null,"abstract":"This paper presents robust speech recognition using a noise suppression method based on multi-model compositions and multi-pass search. In real environments, many kinds of noise signals exists, and input speech for speech recognition systems include them. Our task in the E-Nightingale project is speech recognition of voice memoranda spoken by nurses during actual work at hospitals. To obtain good recognized candidates, suppressing many kinds of noise signals at once to find target speech is important. First, before noise suppression, to find speech and noise label sequences, we introduce multi-pass search with acoustic models including many kinds of noise models and their compositions, their n-gram models, and their lexicon. Second, noise suppression based on models is performed using the multiple composite models selected by recognized label sequences with time alignments. We evaluated this approach using the E-Nightingale task, and the proposed method outperformed the conventional method.","PeriodicalId":371729,"journal":{"name":"2007 IEEE Workshop on Automatic Speech Recognition & Understanding (ASRU)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117006625","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：