• Publications
  • Influence
SRILM - an extensible language modeling toolkit
The functionality of the SRILM toolkit is summarized and its design and implementation is discussed, highlighting ease of rapid prototyping, reusability, and combinability of tools. Expand
Dialogue act modeling for automatic tagging and recognition of conversational speech
A probabilistic integration of speech recognition with dialogue modeling is developed, to improve both speech recognition and dialogue act classification accuracy. Expand
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 the speech recognition output and obtain a more perspicuous representation of a set of alternativeExpand
Within-class covariance normalization for SVM-based speaker recognition
A practical procedure for applying WCCN to an SVM-based speaker recognition system where the input feature vectors reside in a high-dimensional space and achieves improvements of up to 22% in EER and 28% in minimum decision cost function (DCF) over the previous baseline. Expand
The ICSI Meeting Corpus
A corpus of data from natural meetings that occurred at the International Computer Science Institute in Berkeley, California over the last three years is collected, which supports work in automatic speech recognition, noise robustness, dialog modeling, prosody, rich transcription, information retrieval, and more. Expand
An Efficient Probabilistic Context-Free Parsing Algorithm that Computes Prefix Probabilities
  • A. Stolcke
  • Computer Science
  • Comput. Linguistics
  • 28 November 1994
An extension of Earley's parser for stochastic context-free grammars that computes probabilities of successive prefixes being generated by the grammar and an input string and posterior expected number of applications of each grammar production, as required for reestimating rule probabilities. Expand
Prosody-based automatic detection of annoyance and frustration in human-computer dialog
Results show that a prosodic model can predict whether an utterance is neutral ve sus “annoyed or frustrated” with an accuracy on par with that of human interlabeler agreement. Expand
Prosody-based automatic segmentation of speech into sentences and topics
This work combines prosodic cues with word-based approaches, and evaluates performance on two speech corpora, Broadcast News and Switchboard, finding that the prosodic model achieves comparable performance with significantly less training data, and requires no hand-labeling of prosodic events. Expand
Bayesian learning of probabilistic language models
A version of Earley's parser is presented that solves the standard problems associated with SCFGs efficiently, including the computation of sentence probabilities and sentence prefix probabilities, finding most likely parses, and the estimation of grammar parameters. Expand
Can Prosody Aid the Automatic Classification of Dialog Acts in Conversational Speech?
It is suggested that DAs are redundantly marked in natural conversation, and that a variety of automatically extractable prosodic features could aid dialog processing in speech applications. Expand