Super-human multi-talker speech recognition: The IBM 2006 speech separation challenge system

Super-human multi-talker speech recognition: The IBM 2006 speech separation challenge system (2006)

by T. Kristjansson , J. Hershey , P. Olsen , S. Rennie , R. Gopinath

Venue:	in ICSLP
Citations:	23 - 2 self

Datum	Value	Source
TITLE	Super-human multi-talker speech recognition: The IBM 2006 speech separation challenge system	INFERENCE
AUTHOR NAME	T. Kristjansson	SVM HeaderParse 0.2
AUTHOR NAME	J. Hershey	SVM HeaderParse 0.2
AUTHOR NAME	P. Olsen	SVM HeaderParse 0.2
AUTHOR NAME	S. Rennie	SVM HeaderParse 0.2
AUTHOR NAME	R. Gopinath	SVM HeaderParse 0.2
ABSTRACT	We describe a system for model based speech separation which achieves super-human recognition performance when two talkers speak at similar levels. The system can separate the speech of two speakers from a single channel recording with remarkable results. It incorporates a novel method for performing two-talker speaker identification and gain estimation. We extend the method of model based high resolution signal reconstruction to incorporate temporal dynamics. We report on two methods for introducing dynamics; the first uses dynamics in the acoustic model space, the second incorporates dynamics based on sentence grammar. The addition of temporal constraints leads to dramatic improvements in the separation performance. Once the signals have been separated they are then recognized using speaker dependent labeling. 1.	SVM HeaderParse 0.2
YEAR	2006	INFERENCE
VENUE	in ICSLP	INFERENCE
VENUE TYPE	CONFERENCE	INFERENCE
PAGES	97--100	INFERENCE
CITATIONS	6 found	ParsCit 1.0