Recognition of conversational telephone speech using the JANUS speech engine

Recognition of conversational speech is one of the most challenging speech recognition tasks to-date. While recognition error rates of 10% or lower can now be reached on speech dictation tasks over vocabularies in excess of 60,000 words, recognition of conversational speech has persistently resisted...

Full description

Saved in:
Bibliographic Details
Main Authors: Zeppenfeld, T., Finke, M., Ries, K., Westphal, M., Waibel, A.
Format: Conference Proceeding
Language:English
Subjects:
Applied sciences
Artificial intelligence
Boosting
Computer science
control theory
systems
Degradation
Engines
Error analysis
Exact sciences and technology
Information, signal and communications theory
Length measurement
NIST
Signal processing
Speech and sound recognition and synthesis. Linguistics
Speech processing
Speech processing and communication systems
Speech recognition
Telecommunications and information theory
Telephony
Testing
Vocabulary
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Recognition of conversational speech is one of the most challenging speech recognition tasks to-date. While recognition error rates of 10% or lower can now be reached on speech dictation tasks over vocabularies in excess of 60,000 words, recognition of conversational speech has persistently resisted most attempts at improvements by way of the proven techniques to date. Difficulties arise from shorter words, telephone channel degradation, and highly disfluent and coarticulated speech. In this paper, we describe the application, adaptation, and performance evaluation of our JANUS speech recognition engine to the Switchboard conversational speech recognition task. Through a number of algorithmic improvements, we have been able to reduce error rates from more than 50% word error to 38%, measured on the offical 1996 NIST evaluation test set. Improvements include vocal tract length normalization, polyphonic modeling, label boosting, speaker adaptation with and without confidence measures, and speaking mode dependent pronunciation modeling.
ISSN:1520-6149
2379-190X
DOI:10.1109/ICASSP.1997.598889