Recent experiments in Large Vocabulary Conversational Speech Recognition

被引：5

作者：

Billa, J ^{[1
]}

Colhurst, T ^{[1
]}

El-Jaroudi, A ^{[1
]}

Iyer, R ^{[1
]}

Ma, K ^{[1
]}

Matsoukas, S ^{[1
]}

Quillen, C ^{[1
]}

Richardson, F ^{[1
]}

Siu, M ^{[1
]}

Zavaliagkos, G ^{[1
]}

Gish, H ^{[1
]}

机构：

[1] BBN Syst & Technol Corp, Cambridge, MA 02138 USA

来源：

ICASSP '99: 1999 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH, AND SIGNAL PROCESSING, PROCEEDINGS VOLS I-VI | 1999年

关键词：

D O I：

10.1109/ICASSP.1999.758057

中图分类号：

O42 [声学];

学科分类号：

070206 ; 082403 ;

摘要：

This paper describes the improvements that resulted in the 1998 Byblos Large Vocabulary Conversational Speech Recognition (LVCSR) System. Salient among these improvements are: improved signal processing, improved Hidden Markov Model (HMM) topology, use of quinphone context, introduction of diagonal speaker adapted training (DSAT), incorporation of variance adaptation in the MLLR framework, improvements in language modeling, increase in lexicon size and combination of multiple systems. These changes resulted in about a 7% absolute reduction in word error rates on a balanced Switchboard/Callhome English test set.

引用

页码：41 / 44

页数：4