Enriching speech recognition with automatic detection of sentence boundaries and disfluencies
Authors:
- E. ShribergESE. Shriberg
- A. StolckeASA. Stolcke
- D. HillardDHD. Hillard
- M. OstendorfMOM. Ostendorf
- M. HarperMHM. Harper
- 21 August 2006
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Audio, Speech, and Language Processing
- Vol. 14 (5) , 1526-1540
Abstract
Effective human and automatic processing of speech requires recovery of more than just the words. It also involves recovering phenomena such as sentence boundaries, filler words, and disfluencies, referred to as structural metadata. We describe a metadata detection system that combines information from different types of textual knowledge sources with information from a prosodic classifier. We investigate maximum entropy and conditional random field models, as well as the predominant hidden Markov model (HMM) approach, and find that discriminative models generally outperform generative models. We report system performance on both broadcast news and conversational telephone speech tasks, illustrating significant performance differences across tasks and as a function of recognizer performance. The results represent the state of the art, as assessed in the NIST RT-04F evaluationKeywords
This publication has 30 references indexed in Scilit:
- A study in machine learning from imbalanced data for sentence boundary detection in speechComputer Speech & Language, 2006
- A combined punctuation generation and speech recognition system and its performance enhancement using prosodySpeech Communication, 2003
- Finding consensus in speech recognition: word error minimization and other applications of confusion networksComputer Speech & Language, 2000
- Dialogue Act Modeling for Automatic Tagging and Recognition of Conversational SpeechComputational Linguistics, 2000
- Prosody-based automatic segmentation of speech into sentences and topicsSpeech Communication, 2000
- Prosodic features at discourse boundaries of different strengthThe Journal of the Acoustical Society of America, 1997
- On the perceptual strength of prosodic boundaries and its relation to suprasegmental cuesThe Journal of the Acoustical Society of America, 1994
- A corpus-based study of repair cues in spontaneous speechThe Journal of the Acoustical Society of America, 1994
- The use of prosody in syntactic disambiguationThe Journal of the Acoustical Society of America, 1991
- Duration as a cue to the perception of a phrase boundaryThe Journal of the Acoustical Society of America, 1982