Pub Date : 2007-12-13DOI: 10.1109/ASRU.2007.4430167
J. Schatzmann, Blaise Thomson, S. Young
Human-machine dialogue is heavily influenced by speech recognition and understanding errors and it is hence desirable to train and test statistical dialogue system policies under realistic noise conditions. This paper presents a novel approach to error simulation based on statistical models for word-level utterance generation, ASR confusions, and confidence score generation. While the method explicitly models the context-dependent acoustic confusability of words and allows the system specific language model and semantic decoder to be incorporated, it is computationally inexpensive and thus potentially suitable for running thousands of training simulations. Experimental evaluation results with a POMDP-based dialogue system and the Hidden Agenda User Simulator indicate a close match between the statistical properties of real and synthetic errors.
{"title":"Error simulation for training statistical dialogue systems","authors":"J. Schatzmann, Blaise Thomson, S. Young","doi":"10.1109/ASRU.2007.4430167","DOIUrl":"https://doi.org/10.1109/ASRU.2007.4430167","url":null,"abstract":"Human-machine dialogue is heavily influenced by speech recognition and understanding errors and it is hence desirable to train and test statistical dialogue system policies under realistic noise conditions. This paper presents a novel approach to error simulation based on statistical models for word-level utterance generation, ASR confusions, and confidence score generation. While the method explicitly models the context-dependent acoustic confusability of words and allows the system specific language model and semantic decoder to be incorporated, it is computationally inexpensive and thus potentially suitable for running thousands of training simulations. Experimental evaluation results with a POMDP-based dialogue system and the Hidden Agenda User Simulator indicate a close match between the statistical properties of real and synthetic errors.","PeriodicalId":371729,"journal":{"name":"2007 IEEE Workshop on Automatic Speech Recognition & Understanding (ASRU)","volume":"41 12","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-12-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132442498","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 : 2007-12-13DOI: 10.1109/ASRU.2007.4430084
M. Gales, R. V. Dalen
It is well known that the addition of background noise alters the correlations between the elements of, for example, the MFCC feature vector. However, standard model-based compensation techniques do not modify the feature-space in which the diagonal covariance matrix Gaussian mixture models are estimated. One solution to this problem, which yields good performance, is joint uncertainty decoding (JUD) with full transforms. Unfortunately, this results in a high computational cost during decoding. This paper contrasts two approaches to approximating full JUD while lowering the computational cost. Both use predictive linear transforms to modify the feature-space: adaptation-based linear transforms, where the model parameters are restricted to be the same as the original clean system; and precision matrix modelling approaches, in particular semi-tied covariance matrices. These predictive transforms are estimated using statistics derived from the full JUD transforms rather than noisy data. The schemes are evaluated on AURORA 2 and a noise-corrupted resource management task.
{"title":"Predictive linear transforms for noise robust speech recognition","authors":"M. Gales, R. V. Dalen","doi":"10.1109/ASRU.2007.4430084","DOIUrl":"https://doi.org/10.1109/ASRU.2007.4430084","url":null,"abstract":"It is well known that the addition of background noise alters the correlations between the elements of, for example, the MFCC feature vector. However, standard model-based compensation techniques do not modify the feature-space in which the diagonal covariance matrix Gaussian mixture models are estimated. One solution to this problem, which yields good performance, is joint uncertainty decoding (JUD) with full transforms. Unfortunately, this results in a high computational cost during decoding. This paper contrasts two approaches to approximating full JUD while lowering the computational cost. Both use predictive linear transforms to modify the feature-space: adaptation-based linear transforms, where the model parameters are restricted to be the same as the original clean system; and precision matrix modelling approaches, in particular semi-tied covariance matrices. These predictive transforms are estimated using statistics derived from the full JUD transforms rather than noisy data. The schemes are evaluated on AURORA 2 and a noise-corrupted resource management task.","PeriodicalId":371729,"journal":{"name":"2007 IEEE Workshop on Automatic Speech Recognition & Understanding (ASRU)","volume":"26 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-12-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121147483","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 : 2007-12-13DOI: 10.1109/ASRU.2007.4430078
M. Gales, Frank Diehl, C. Raut, M. Tomalin, P. Woodland, Kai Yu
This paper describes the development of an Arabic speech recognition system based on a phonetic dictionary. Though phonetic systems have been previously investigated, this paper makes a number of contributions to the understanding of how to build these systems, as well as describing a complete Arabic speech recognition system. The first issue considered is discriminative training when there are a large number of pronunciation variants for each word. In particular, the loss function associated with minimum phone error (MPE) training is examined. The performance and combination of phonetic and graphemic acoustic models are then compared on both Broadcast News (BN) and Broadcast Conversation (BC) data. The final contribution of the paper is a simple scheme for automatically generating pronunciations for use in training and reducing the phonetic out-of-vocabulary rate. The paper concludes with a description and results from using phonetic and graphemic systems in a multipass/combination framework.
{"title":"Development of a phonetic system for large vocabulary Arabic speech recognition","authors":"M. Gales, Frank Diehl, C. Raut, M. Tomalin, P. Woodland, Kai Yu","doi":"10.1109/ASRU.2007.4430078","DOIUrl":"https://doi.org/10.1109/ASRU.2007.4430078","url":null,"abstract":"This paper describes the development of an Arabic speech recognition system based on a phonetic dictionary. Though phonetic systems have been previously investigated, this paper makes a number of contributions to the understanding of how to build these systems, as well as describing a complete Arabic speech recognition system. The first issue considered is discriminative training when there are a large number of pronunciation variants for each word. In particular, the loss function associated with minimum phone error (MPE) training is examined. The performance and combination of phonetic and graphemic acoustic models are then compared on both Broadcast News (BN) and Broadcast Conversation (BC) data. The final contribution of the paper is a simple scheme for automatically generating pronunciations for use in training and reducing the phonetic out-of-vocabulary rate. The paper concludes with a description and results from using phonetic and graphemic systems in a multipass/combination framework.","PeriodicalId":371729,"journal":{"name":"2007 IEEE Workshop on Automatic Speech Recognition & Understanding (ASRU)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-12-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129392914","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.2007.4430195
Wooil Kim, J. Hansen
This paper presents our recent advances for SpeechFind, a CRSS-UTD designed spoken document retrieval system for the U.S. based Collaborative Digitization Program (CDP). A proto-type of SpeechFind for the CDP is currently serving as the search engine for 1,300 hours of CDP audio content which contain a wide range of acoustic conditions, vocabulary and period selection, and topics. In an effort to determine the amount of user corrected transcripts needed to impact automatic speech recognition (ASR) and audio search, a web-based online interface for verification of ASR-generated transcripts was developed. The procedure for enhancing the transcription performance for SpeechFind is also presented. A selection of adaptation methods for language and acoustic models are employed depending on the acoustics of the corpora under test. Experimental results on the CDP corpus demonstrate that the employed model adaptation scheme using the verified transcripts is effective in improving recognition accuracy. Through a combination of feature/acoustic model enhancement and language model selection, up to 24.8% relative improvement in ASR was obtained. The SpeechFind system, employing automatic transcript generation, online CDP transcript correction, and our transcript reliability estimator, demonstrates a comprehensive support mechanism to ensure reliable transcription and search for U.S. libraries with limited speech technology experience.
{"title":"Speechfind for CDP: Advances in spoken document retrieval for the U. S. collaborative digitization program","authors":"Wooil Kim, J. Hansen","doi":"10.1109/ASRU.2007.4430195","DOIUrl":"https://doi.org/10.1109/ASRU.2007.4430195","url":null,"abstract":"This paper presents our recent advances for SpeechFind, a CRSS-UTD designed spoken document retrieval system for the U.S. based Collaborative Digitization Program (CDP). A proto-type of SpeechFind for the CDP is currently serving as the search engine for 1,300 hours of CDP audio content which contain a wide range of acoustic conditions, vocabulary and period selection, and topics. In an effort to determine the amount of user corrected transcripts needed to impact automatic speech recognition (ASR) and audio search, a web-based online interface for verification of ASR-generated transcripts was developed. The procedure for enhancing the transcription performance for SpeechFind is also presented. A selection of adaptation methods for language and acoustic models are employed depending on the acoustics of the corpora under test. Experimental results on the CDP corpus demonstrate that the employed model adaptation scheme using the verified transcripts is effective in improving recognition accuracy. Through a combination of feature/acoustic model enhancement and language model selection, up to 24.8% relative improvement in ASR was obtained. The SpeechFind system, employing automatic transcript generation, online CDP transcript correction, and our transcript reliability estimator, demonstrates a comprehensive support mechanism to ensure reliable transcription and search for U.S. libraries with limited speech technology experience.","PeriodicalId":371729,"journal":{"name":"2007 IEEE Workshop on Automatic Speech Recognition & Understanding (ASRU)","volume":"10 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":"121031290","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.2007.4430166
T. Cincarek, Hiromichi Kawanami, H. Saruwatari, K. Shikano
In this paper, we investigate development and portability of ASR and Q&A modules of speech-oriented guidance systems for two different real environments. An initial prototype system has been constructed for a local community center using two years of human-labeled data collected by the system. Collection of real user data is required because ASR task and Q&A domain of a guidance system are defined by the target environment and potential users. However, since human preparation of data is always costly, most often only a relatively small amount real data will be available for system adaptation in practice. Therefore, the portability of the initial prototype system is investigated for a different environment, a local subway station. The purpose is to identify reusable system parts. The ASR module is found to be highly portable across the two environments. However, the portability of the Q&A module was only medium. From an objective analysis it became clear that this is mainly due to the environment-dependent domain differences between the two systems. This implicates that it will always be important to take the behavior of actual users under real conditions into account to build a system with high user satisfaction.
{"title":"Development and portability of ASR and Q&A modules for real-environment speech-oriented guidance systems","authors":"T. Cincarek, Hiromichi Kawanami, H. Saruwatari, K. Shikano","doi":"10.1109/ASRU.2007.4430166","DOIUrl":"https://doi.org/10.1109/ASRU.2007.4430166","url":null,"abstract":"In this paper, we investigate development and portability of ASR and Q&A modules of speech-oriented guidance systems for two different real environments. An initial prototype system has been constructed for a local community center using two years of human-labeled data collected by the system. Collection of real user data is required because ASR task and Q&A domain of a guidance system are defined by the target environment and potential users. However, since human preparation of data is always costly, most often only a relatively small amount real data will be available for system adaptation in practice. Therefore, the portability of the initial prototype system is investigated for a different environment, a local subway station. The purpose is to identify reusable system parts. The ASR module is found to be highly portable across the two environments. However, the portability of the Q&A module was only medium. From an objective analysis it became clear that this is mainly due to the environment-dependent domain differences between the two systems. This implicates that it will always be important to take the behavior of actual users under real conditions into account to build a system with high user satisfaction.","PeriodicalId":371729,"journal":{"name":"2007 IEEE Workshop on Automatic Speech Recognition & Understanding (ASRU)","volume":"56 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":"124965120","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.2007.4430117
S. Furui, Tetsunori Kobayashi
Summary form only given. Waseda University, Tokyo Institute of Technology, and six companies, Asahi-kasei, Hitachi, Mitsubishi, NEC, Oki and Toshiba, initiated a three year project in 2006 supported by the ministry of economy, industry and trade (METI), Japan, for jointly developing fundamental automatic speech recognition (ASR) technology. The project focuses on utilizing ASR technology in car and home environments. Seven subtasks are being investigated: speech/non-speech separation using multiple microphones, speech/non-speech separation for a single audio stream, developing a high-performance WFST-based decoder, multi-lingual ASR modeling, higher-order language modeling, developing a system for assisting speech interface development, and overall technology evaluation. This talk will give an overview of the intermediate technological progress achieved by the project.
{"title":"Introduction of the METI project “development of fundamental speech recognition technology”","authors":"S. Furui, Tetsunori Kobayashi","doi":"10.1109/ASRU.2007.4430117","DOIUrl":"https://doi.org/10.1109/ASRU.2007.4430117","url":null,"abstract":"Summary form only given. Waseda University, Tokyo Institute of Technology, and six companies, Asahi-kasei, Hitachi, Mitsubishi, NEC, Oki and Toshiba, initiated a three year project in 2006 supported by the ministry of economy, industry and trade (METI), Japan, for jointly developing fundamental automatic speech recognition (ASR) technology. The project focuses on utilizing ASR technology in car and home environments. Seven subtasks are being investigated: speech/non-speech separation using multiple microphones, speech/non-speech separation for a single audio stream, developing a high-performance WFST-based decoder, multi-lingual ASR modeling, higher-order language modeling, developing a system for assisting speech interface development, and overall technology evaluation. This talk will give an overview of the intermediate technological progress achieved by the project.","PeriodicalId":371729,"journal":{"name":"2007 IEEE Workshop on Automatic Speech Recognition & Understanding (ASRU)","volume":"33 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":"125111425","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.2007.4430175
Qiang Fu, B. Juang
This paper presents an investigation of the rescoring performance using hidden Markov model (HMM) based attribute detectors. The minimum verification error (MVE) criterion is employed to enhance the reliability of the detectors in continuous speech recognition. The HMM-based detectors are applied on the possible recognition candidates, which are generated from the conventional decoder and organized in phone/word graphs. We focus on the study of rescoring performance with the detectors trained on the tokens produced by the decoder but labeled in broad phonetic categories rather than the phonetic identities. Various training criteria and knowledge fusion methods are investigated under various semantic level rescoring scenarios. This research demonstrates various possibilities of embedding auxiliary information into the current automatic speech recognition (ASR) framework for improved results. It also represents an intermediate step towards the construction of a true detection-based ASR paradigm.
{"title":"A study on rescoring using HMM-based detectors for continuous speech recognition","authors":"Qiang Fu, B. Juang","doi":"10.1109/ASRU.2007.4430175","DOIUrl":"https://doi.org/10.1109/ASRU.2007.4430175","url":null,"abstract":"This paper presents an investigation of the rescoring performance using hidden Markov model (HMM) based attribute detectors. The minimum verification error (MVE) criterion is employed to enhance the reliability of the detectors in continuous speech recognition. The HMM-based detectors are applied on the possible recognition candidates, which are generated from the conventional decoder and organized in phone/word graphs. We focus on the study of rescoring performance with the detectors trained on the tokens produced by the decoder but labeled in broad phonetic categories rather than the phonetic identities. Various training criteria and knowledge fusion methods are investigated under various semantic level rescoring scenarios. This research demonstrates various possibilities of embedding auxiliary information into the current automatic speech recognition (ASR) framework for improved results. It also represents an intermediate step towards the construction of a true detection-based ASR paradigm.","PeriodicalId":371729,"journal":{"name":"2007 IEEE Workshop on Automatic Speech Recognition & Understanding (ASRU)","volume":"5 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":"115515157","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.2007.4430197
K. Markov, Satoshi Nakamura
In this paper, we describe new high-performance on-line speaker diarization system which works faster than real-time and has very low latency. It consists of several modules including voice activity detection, novel speaker detection, speaker gender and speaker identity classification. All modules share a set of Gaussian mixture models (GMM) representing pause, male and female speakers, and each individual speaker. Initially, there are only three GMMs for pause and two speaker genders, trained in advance from some data. During the speaker diarization process, for each speech segment it is decided whether it comes from a new speaker or from already known speaker. In case of a new speaker, his/her gender is identified, and then, from the corresponding gender GMM, a new GMM is spawned by copying its parameters. This GMM is learned on-line using the speech segment data and from this point it is used to represent the new speaker. All individual speaker models are produced in this way. In the case of an old speaker, s/he is identified and the corresponding GMM is again learned on-line. In order to prevent an unlimited grow of the speaker model number, those models that have not been selected as winners for a long period of time are deleted from the system. This allows the system to be able to perform its task indefinitely in addition to being capable of self-organization, i.e. unsupervised adaptive learning, and preservation of the learned knowledge, i.e. speakers. Such functionalities are attributed to the so called Never-Ending Learning systems. For evaluation, we used part of the TC-STAR database consisting of European Parliament Plenary speeches. The results show that this system achieves a speaker diarization error rate of 4.6% with latency of at most 3 seconds.
{"title":"Never-ending learning system for on-line speaker diarization","authors":"K. Markov, Satoshi Nakamura","doi":"10.1109/ASRU.2007.4430197","DOIUrl":"https://doi.org/10.1109/ASRU.2007.4430197","url":null,"abstract":"In this paper, we describe new high-performance on-line speaker diarization system which works faster than real-time and has very low latency. It consists of several modules including voice activity detection, novel speaker detection, speaker gender and speaker identity classification. All modules share a set of Gaussian mixture models (GMM) representing pause, male and female speakers, and each individual speaker. Initially, there are only three GMMs for pause and two speaker genders, trained in advance from some data. During the speaker diarization process, for each speech segment it is decided whether it comes from a new speaker or from already known speaker. In case of a new speaker, his/her gender is identified, and then, from the corresponding gender GMM, a new GMM is spawned by copying its parameters. This GMM is learned on-line using the speech segment data and from this point it is used to represent the new speaker. All individual speaker models are produced in this way. In the case of an old speaker, s/he is identified and the corresponding GMM is again learned on-line. In order to prevent an unlimited grow of the speaker model number, those models that have not been selected as winners for a long period of time are deleted from the system. This allows the system to be able to perform its task indefinitely in addition to being capable of self-organization, i.e. unsupervised adaptive learning, and preservation of the learned knowledge, i.e. speakers. Such functionalities are attributed to the so called Never-Ending Learning systems. For evaluation, we used part of the TC-STAR database consisting of European Parliament Plenary speeches. The results show that this system achieves a speaker diarization error rate of 4.6% with latency of at most 3 seconds.","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":"129426523","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.2007.4430096
Songfang Huang, S. Renals
In this paper we investigate the application of a hierarchical Bayesian language model (LM) based on the Pitman-Yor process for automatic speech recognition (ASR) of multiparty meetings. The hierarchical Pitman-Yor language model (HPY-LM) provides a Bayesian interpretation of LM smoothing. An approximation to the HPYLM recovers the exact formulation of the interpolated Kneser-Ney smoothing method in n-gram models. This paper focuses on the application and scalability of HPYLM on a practical large vocabulary ASR system. Experimental results on NIST RT06s evaluation meeting data verify that HPYLM is a competitive and promising language modeling technique, which consistently performs better than interpolated Kneser-Ney and modified Kneser-Ney n-gram LMs in terms of both perplexity and word error rate.
{"title":"Hierarchical Pitman-Yor language models for ASR in meetings","authors":"Songfang Huang, S. Renals","doi":"10.1109/ASRU.2007.4430096","DOIUrl":"https://doi.org/10.1109/ASRU.2007.4430096","url":null,"abstract":"In this paper we investigate the application of a hierarchical Bayesian language model (LM) based on the Pitman-Yor process for automatic speech recognition (ASR) of multiparty meetings. The hierarchical Pitman-Yor language model (HPY-LM) provides a Bayesian interpretation of LM smoothing. An approximation to the HPYLM recovers the exact formulation of the interpolated Kneser-Ney smoothing method in n-gram models. This paper focuses on the application and scalability of HPYLM on a practical large vocabulary ASR system. Experimental results on NIST RT06s evaluation meeting data verify that HPYLM is a competitive and promising language modeling technique, which consistently performs better than interpolated Kneser-Ney and modified Kneser-Ney n-gram LMs in terms of both perplexity and word error rate.","PeriodicalId":371729,"journal":{"name":"2007 IEEE Workshop on Automatic Speech Recognition & Understanding (ASRU)","volume":"71 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":"123155807","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.2007.4430104
Jia Cui, Yi Su, Keith B. Hall, F. Jelinek
We present a novel language model capable of incorporating various types of linguistic information as encoded in the form of a token, a (word, label)-tuple. Using tokens as hidden states, our model is effectively a hidden Markov model (HMM) producing sequences of words with trivial output distributions. The transition probabilities, however, are computed using a maximum entropy model to take advantage of potentially overlapping features. We investigated different types of labels with a wide range of linguistic implications. These models outperform Kneser-Ney smoothed n-gram models both in terms of perplexity on standard datasets and in terms of word error rate for a large vocabulary speech recognition system.
{"title":"Investigating linguistic knowledge in a maximum entropy token-based language model","authors":"Jia Cui, Yi Su, Keith B. Hall, F. Jelinek","doi":"10.1109/ASRU.2007.4430104","DOIUrl":"https://doi.org/10.1109/ASRU.2007.4430104","url":null,"abstract":"We present a novel language model capable of incorporating various types of linguistic information as encoded in the form of a token, a (word, label)-tuple. Using tokens as hidden states, our model is effectively a hidden Markov model (HMM) producing sequences of words with trivial output distributions. The transition probabilities, however, are computed using a maximum entropy model to take advantage of potentially overlapping features. We investigated different types of labels with a wide range of linguistic implications. These models outperform Kneser-Ney smoothed n-gram models both in terms of perplexity on standard datasets and in terms of word error rate for a large vocabulary speech recognition system.","PeriodicalId":371729,"journal":{"name":"2007 IEEE Workshop on Automatic Speech Recognition & Understanding (ASRU)","volume":"5 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":"121376553","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：