Acoustic Modeling for the SRI Hub4 Partitioned Evaluation Continuous Speech Recognition System

Acoustic Modeling for the SRI Hub4 Partitioned Evaluation Continuous Speech Recognition System (1997)

Cached

Download Links

by Ananth Sankar , Larry Heck , Andreas Stolcke

Venue:	In Proceedings of the DARPA Speech Recognition Workshop
Citations:	5 - 4 self

Versions

Version History

Metadata Version 3

User correction supplied by SystemCorrections

Datum	Value	Source
TITLE	Acoustic Modeling for the SRI Hub4 Partitioned Evaluation Continuous Speech Recognition System	user correction - Legacy Corrections
AUTHOR NAME	Ananth Sankar	SVM HeaderParse 0.1
AUTHOR AFFIL	Speech Technology And Research Laboratory; SRI International	SVM HeaderParse 0.2
AUTHOR ADDR	Menlo Park, California	SVM HeaderParse 0.1
AUTHOR NAME	Larry Heck	SVM HeaderParse 0.1
AUTHOR AFFIL	Speech Technology And Research Laboratory; SRI International	SVM HeaderParse 0.2
AUTHOR ADDR	Menlo Park, California	SVM HeaderParse 0.1
AUTHOR NAME	Andreas Stolcke	SVM HeaderParse 0.1
AUTHOR AFFIL	Speech Technology And Research Laboratory; SRI International	SVM HeaderParse 0.2
AUTHOR ADDR	Menlo Park, California	SVM HeaderParse 0.1
ABSTRACT	We describe the development of the SRI systemevaluated in the 1996 DARPA continuous speechrecognition (CSR) Hub4 partitioned evaluation (PE). The task for the Hub4evaluation was to recognize speech from broadcast television and radio shows. Recognizingsuch speech by machines poses many challenges. First, the segments to be recognized could be very long. This introduces a problem in training and recognition becauseof the consequentincreasedsystem memory requirement. A simple segmentation technique is used to break long segments into shorter, more manageable lengths. The speech from broadcast news sources exhibits a variety of difficult acoustic conditions, such as spontaneous speech, band-limited speech, and speech in the presence of noise, music, or background speakers. Such background conditions lead to significant degradation in performance. We describe techniques, based on acoustic adaptation, that adapt recognition models to the different acoustic background conditions, so as to im...	user correction - Legacy Corrections
YEAR	1997	INFERENCE
VENUE	In Proceedings of the DARPA Speech Recognition Workshop	INFERENCE
VENUE TYPE	CONFERENCE	INFERENCE
PAGES	127--132	INFERENCE
CITATIONS	10 found	ParsCit 1.0