Recent progress in robust vocabulary-independent speech recognition

Recent progress in robust vocabulary-independent speech recognition (1991)

Cached

Download Links

[acl.ldc.upenn.edu]

Other Repositories/Bibliography

DBLP

by Hsiao-wuen Hon , Kai. Fu Lee

Venue:	Proceedings DARPA Speech and Natural Language Processing Workshop
Citations:	7 - 0 self

Versions

Version History

Metadata Version 1

Datum	Value	Source
TITLE	Recent progress in robust vocabulary-independent speech recognition	INFERENCE
AUTHOR NAME	Hsiao-wuen Hon	SVM HeaderParse 0.2
AUTHOR AFFIL	School of Computer Science; Carnegie Mellon University	SVM HeaderParse 0.2
AUTHOR ADDR	Pittsburgh, Pennsylvania 15213	SVM HeaderParse 0.2
AUTHOR NAME	Kai. Fu Lee	SVM HeaderParse 0.2
AUTHOR AFFIL	School of Computer Science; Carnegie Mellon University	SVM HeaderParse 0.2
AUTHOR ADDR	Pittsburgh, Pennsylvania 15213	SVM HeaderParse 0.2
ABSTRACT	This paper reports recent efforts to improve the performance of CMU's robust vocabulary-independent (VI) speech recognition systems on the DARPA speaker-independent resource management task. The improvements are evaluated on 320 sentences that randomly selected from the DARPA June 88, February 89 and October 89 test sets. Our first improvement involves more detailed acoustic modeling. We incorporated more dynamic features computed from the LPC cepstra and reduced error by 15 % over the baseline system. Our second improvement comes from a larger training database. With more training data, our third improvement comes from a more detailed subword modeling. We incorporated the word boundary context into our VI subword modeling and it resulted in a 30 % error reduction. Finally, we used decision-tree allophone clustering to find more suitable models for the subword units not covered in the training set and further reduced error by 17%. All the techniques combined reduced the VI error rate on the resource management task from 11.1 % to 5.4 % (and from 15.4 % to 7.4 % when training and testing were under different recording environment). This vocabulary-independent performance has exceeded our vocabulary-dependent performance.	SVM HeaderParse 0.2
YEAR	1991	INFERENCE
VENUE	Proceedings DARPA Speech and Natural Language Processing Workshop	INFERENCE
VENUE TYPE	CONFERENCE	INFERENCE
PAGES	258--263	INFERENCE
CITATIONS	14 found	ParsCit 1.0