Andreas Stolcke
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Andreas Stolcke has a total of 25 co-authors. Here are the top co-authors by number of shared publications:
Elizabeth Shriberg
SRI International
2 shared publicationsC. Van Ess-Dykema
1 shared publicationCarol Van Ess-Dykema
U.S. Department of Defense
1 shared publicationD. Jurafsky
1 shared publicationDaniel Jurafsky
University of Colorado at Boulder
1 shared publicationE. Shriberg
1 shared publication
Latest Publications
- 1 April 2007
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 4 (15206149) , IV-173-173
Unsupervised Languagemodel Adaptation for Meeting Recognition
We present an application of unsupervised language model (ML) adaptation to meeting recognition, in a scenario where sequences of multiparty meetings on related topics are to be recognized, but no prior in-domain data for LM training is available. The recognizer LMs are adapted according to the recognition output on temporally preceding meetings, either in speaker-dependent or speaker-independent mode. Model adaptation is carried out by interpolating the n-gram probabilities of a large generic LM with those of a small LM estimated from adaptation data, and minimizing perplexity on the automatic transcripts of a separate meeting set, also previously recognized. The adapted LMs yield about 5.9% relative reduction in word error compared to the baseline. This improvement is about half of what can be achieved with supervised adaptation, i.e. using human-generated speech transcripts.
- 1 April 2007
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 4 (15206149) , IV-173-173
Unsupervised Languagemodel Adaptation for Meeting Recognition
We present an application of unsupervised language model (ML) adaptation to meeting recognition, in a scenario where sequences of multiparty meetings on related topics are to be recognized, but no prior in-domain data for LM training is available. The recognizer LMs are adapted according to the recognition output on temporally preceding meetings, either in speaker-dependent or speaker-independent mode. Model adaptation is carried out by interpolating the n-gram probabilities of a large generic LM with those of a small LM estimated from adaptation data, and minimizing perplexity on the automatic transcripts of a separate meeting set, also previously recognized. The adapted LMs yield about 5.9% relative reduction in word error compared to the baseline. This improvement is about half of what can be achieved with supervised adaptation, i.e. using human-generated speech transcripts.
- 1 June 2006
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-6
Improvements in MLLR-Transform-based Speaker Recognition
We previously proposed the use of MLLR transforms derived from a speech recognition system as speaker features in a speaker verification system. In this paper we report recent improvements to this approach. First, we noticed a fundamental problem in our previous implementation that stemmed from a mismatch between male and female recognition models, and the model transforms they produce. Although it affects only a small percentage of verification trials (those in which the gender detector commits errors), this mismatch has a large effect on average system performance. We solve this problem by consistently using only one recognition model (either male or female) in computing speaker adaptation transforms regardless of estimated speaker gender. A further accuracy boost is obtained by combining feature vectors derived from male and female vectors into one larger feature vector. Using 1-conversation-side training, the final system has about 27% lower decision cost than a state-of-the-art ccpstral GMM speaker system, and 53% lower decision cost when trained on 8 conversation sides per speaker
- 1 June 2006
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-6
Improvements in MLLR-Transform-based Speaker Recognition
We previously proposed the use of MLLR transforms derived from a speech recognition system as speaker features in a speaker verification system. In this paper we report recent improvements to this approach. First, we noticed a fundamental problem in our previous implementation that stemmed from a mismatch between male and female recognition models, and the model transforms they produce. Although it affects only a small percentage of verification trials (those in which the gender detector commits errors), this mismatch has a large effect on average system performance. We solve this problem by consistently using only one recognition model (either male or female) in computing speaker adaptation transforms regardless of estimated speaker gender. A further accuracy boost is obtained by combining feature vectors derived from male and female vectors into one larger feature vector. Using 1-conversation-side training, the final system has about 27% lower decision cost than a state-of-the-art ccpstral GMM speaker system, and 53% lower decision cost when trained on 8 conversation sides per speaker
- 1 January 2004
- Published by Springer Nature
- p. 105-114
Prosody Modeling for Automatic Speech Recognition and Understanding
- 1 January 2004
- Published by Springer Nature
- p. 105-114
Prosody Modeling for Automatic Speech Recognition and Understanding
- Open Access
Dialogue Act Modeling for Automatic Tagging and Recognition of Conversational Speech
We describe a statistical approach for modeling dialogue acts in conversational speech, i.e., speech-act-like units such as Statement, Question, Backchannel, Agreement, Disagreement, and Apology. Our model detects and predicts dialogue acts based on lexical, collocational, and prosodic cues, as well as on the discourse coherence of the dialogue act sequence. The dialogue model is based on treating the discourse structure of a conversation as a hidden Markov model and the individual dialogue acts as observations emanating from the model states. Constraints on the likely sequence of dialogue acts are modeled via a dialogue act n-gram. The statistical dialogue grammar is combined with word n-grams, decision trees, and neural networks modeling the idiosyncratic lexical and prosodic manifestations of each dialogue act. We develop a probabilistic integration of speech recognition with dialogue modeling, to improve both speech recognition and dialogue act classification accuracy. Models are trained and evaluated using a large hand-labeled database of 1,155 conversations from the Switchboard corpus of spontaneous human-to-human telephone speech. We achieved good dialogue act labeling accuracy (65% based on errorful, automatically recognized words and prosody, and 71% based on word transcripts, compared to a chance baseline accuracy of 35% and human accuracy of 84%) and a small reduction in word recognition error.
Open AccessDialogue Act Modeling for Automatic Tagging and Recognition of Conversational Speech
We describe a statistical approach for modeling dialogue acts in conversational speech, i.e., speech-act-like units such as Statement, Question, Backchannel, Agreement, Disagreement, and Apology. Our model detects and predicts dialogue acts based on lexical, collocational, and prosodic cues, as well as on the discourse coherence of the dialogue act sequence. The dialogue model is based on treating the discourse structure of a conversation as a hidden Markov model and the individual dialogue acts as observations emanating from the model states. Constraints on the likely sequence of dialogue acts are modeled via a dialogue act n-gram. The statistical dialogue grammar is combined with word n-grams, decision trees, and neural networks modeling the idiosyncratic lexical and prosodic manifestations of each dialogue act. We develop a probabilistic integration of speech recognition with dialogue modeling, to improve both speech recognition and dialogue act classification accuracy. Models are trained and evaluated using a large hand-labeled database of 1,155 conversations from the Switchboard corpus of spontaneous human-to-human telephone speech. We achieved good dialogue act labeling accuracy (65% based on errorful, automatically recognized words and prosody, and 71% based on word transcripts, compared to a chance baseline accuracy of 35% and human accuracy of 84%) and a small reduction in word recognition error.
- Open Access
Finding consensus in speech recognition: word error minimization and other applications of confusion networks
We describe a new framework for distilling information from word lattices to improve the accuracy of speech recognition and obtain a more perspicuous representation of a set of alternative hypotheses. In the standard MAP decoding approach the recognizer outputs the string of words corresponding to the path with the highest posterior probability given the acoustics and a language model. However, even given optimal models, the MAP decoder does not necessarily minimize the commonly used performance metric, word error rate (WER). We describe a method for explicitly minimizing WER by extracting word hypotheses with the highest posterior probabilities from word lattices. We change the standard problem formulation by replacing global search over a large set of sentence hypotheses with local search over a small set of word candidates. In addition to improving the accuracy of the recognizer, our method produces a new representation of the set of candidate hypotheses that specifies the sequence of word-level confusions in a compact lattice format. We study the properties of confusion networks and examine their use for other tasks, such as lattice compression, word spotting, confidence annotation, and reevaluation of recognition hypotheses using higher-level knowledge sources.
Open AccessFinding consensus in speech recognition: word error minimization and other applications of confusion networks
We describe a new framework for distilling information from word lattices to improve the accuracy of speech recognition and obtain a more perspicuous representation of a set of alternative hypotheses. In the standard MAP decoding approach the recognizer outputs the string of words corresponding to the path with the highest posterior probability given the acoustics and a language model. However, even given optimal models, the MAP decoder does not necessarily minimize the commonly used performance metric, word error rate (WER). We describe a method for explicitly minimizing WER by extracting word hypotheses with the highest posterior probabilities from word lattices. We change the standard problem formulation by replacing global search over a large set of sentence hypotheses with local search over a small set of word candidates. In addition to improving the accuracy of the recognizer, our method produces a new representation of the set of candidate hypotheses that specifies the sequence of word-level confusions in a compact lattice format. We study the properties of confusion networks and examine their use for other tasks, such as lattice compression, word spotting, confidence annotation, and reevaluation of recognition hypotheses using higher-level knowledge sources.
- Top Cited PapersOpen Access
- 1 September 2000
- Published by MIT Press in Computational Linguistics
- Vol. 26 (3) , 339-373
Dialogue Act Modeling for Automatic Tagging and Recognition of Conversational Speech
We describe a statistical approach for modeling dialogue acts in conversational speech, i.e., speech-act-like units such as STATEMENT, Question, BACKCHANNEL, Agreement, Disagreement, and Apology. Our model detects and predicts dialogue acts based on lexical, collocational, and prosodic cues, as well as on the discourse coherence of the dialogue act sequence. The dialogue model is based on treating the discourse structure of a conversation as a hidden Markov model and the individual dialogue acts as observations emanating from the model states. Constraints on the likely sequence of dialogue acts are modeled via a dialogue act n-gram. The statistical dialogue grammar is combined with word n-grams, decision trees, and neural networks modeling the idiosyncratic lexical and prosodic manifestations of each dialogue act. We develop a probabilistic integration of speech recognition with dialogue modeling, to improve both speech recognition and dialogue act classification accuracy. Models are trained and evaluated using a large hand-labeled database of 1,155 conversations from the Switchboard corpus of spontaneous human-to-human telephone speech. We achieved good dialogue act labeling accuracy (65% based on errorful, automatically recognized words and prosody, and 71% based on word transcripts, compared to a chance baseline accuracy of 35% and human accuracy of 84%) and a small reduction in word recognition error.
- 1 September 2000
- Published by MIT Press in Computational Linguistics
- Vol. 26 (3) , 339-373
Top Cited PapersOpen AccessDialogue Act Modeling for Automatic Tagging and Recognition of Conversational Speech
We describe a statistical approach for modeling dialogue acts in conversational speech, i.e., speech-act-like units such as STATEMENT, Question, BACKCHANNEL, Agreement, Disagreement, and Apology. Our model detects and predicts dialogue acts based on lexical, collocational, and prosodic cues, as well as on the discourse coherence of the dialogue act sequence. The dialogue model is based on treating the discourse structure of a conversation as a hidden Markov model and the individual dialogue acts as observations emanating from the model states. Constraints on the likely sequence of dialogue acts are modeled via a dialogue act n-gram. The statistical dialogue grammar is combined with word n-grams, decision trees, and neural networks modeling the idiosyncratic lexical and prosodic manifestations of each dialogue act. We develop a probabilistic integration of speech recognition with dialogue modeling, to improve both speech recognition and dialogue act classification accuracy. Models are trained and evaluated using a large hand-labeled database of 1,155 conversations from the Switchboard corpus of spontaneous human-to-human telephone speech. We achieved good dialogue act labeling accuracy (65% based on errorful, automatically recognized words and prosody, and 71% based on word transcripts, compared to a chance baseline accuracy of 35% and human accuracy of 84%) and a small reduction in word recognition error.
- 1 October 1996
- Published by Acoustical Society of America (ASA) in The Journal of the Acoustical Society of America
- Vol. 100 (4_Suppleme) , 2848
Integrated acoustic and language modeling of speech disfluencies
- 1 October 1996
- Published by Acoustical Society of America (ASA) in The Journal of the Acoustical Society of America
- Vol. 100 (4_Suppleme) , 2848
Integrated acoustic and language modeling of speech disfluencies
- Open Access
An Efficient Probabilistic Context-Free Parsing Algorithm that Computes Prefix Probabilities
We describe an extension of Earley's parser for stochastic context-free grammars that computes the following quantities given a stochastic context-free grammar and an input string: a) probabilities of successive prefixes being generated by the grammar; b) probabilities of substrings being generated by the nonterminals, including the entire string being generated by the grammar; c) most likely (Viterbi) parse of the string; d) posterior expected number of applications of each grammar production, as required for reestimating rule probabilities. (a) and (b) are computed incrementally in a single left-to-right pass over the input. Our algorithm compares favorably to standard bottom-up parsing methods for SCFGs in that it works efficiently on sparse grammars by making use of Earley's top-down control structure. It can process any context-free rule format without conversion to some normal form, and combines computations for (a) through (d) in a single algorithm. Finally, the algorithm has simple extensions for processing partially bracketed inputs, and for finding partial parses and their likelihoods on ungrammatical inputs.
Open AccessAn Efficient Probabilistic Context-Free Parsing Algorithm that Computes Prefix Probabilities
We describe an extension of Earley's parser for stochastic context-free grammars that computes the following quantities given a stochastic context-free grammar and an input string: a) probabilities of successive prefixes being generated by the grammar; b) probabilities of substrings being generated by the nonterminals, including the entire string being generated by the grammar; c) most likely (Viterbi) parse of the string; d) posterior expected number of applications of each grammar production, as required for reestimating rule probabilities. (a) and (b) are computed incrementally in a single left-to-right pass over the input. Our algorithm compares favorably to standard bottom-up parsing methods for SCFGs in that it works efficiently on sparse grammars by making use of Earley's top-down control structure. It can process any context-free rule format without conversion to some normal form, and combines computations for (a) through (d) in a single algorithm. Finally, the algorithm has simple extensions for processing partially bracketed inputs, and for finding partial parses and their likelihoods on ungrammatical inputs.