Recent improvements of the RWTH large vocabulary speech recognition system on spontaneous speech

被引：0

作者：

Sixtus, A ^{[1
]}

Molau, S ^{[1
]}

Kanthak, S ^{[1
]}

Schlüter, R ^{[1
]}

Ney, H ^{[1
]}

机构：

[1] RWTH Aachen Univ Technol, Lehrstuhl Informat VI, D-52056 Aachen, Germany

来源：

2000 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH, AND SIGNAL PROCESSING, PROCEEDINGS, VOLS I-VI | 2000年

关键词：

D O I：

暂无

中图分类号：

O42 [声学];

学科分类号：

070206 ; 082403 ;

摘要：

This paper presents recent improvements of the RWTH large vocabulary continuous speech recognition system (LSCSR). In particular, we will report on the integration of across-word models into the first recognition pass, and describe better algorithms for fast vocal tract normalization (VTN). We will focus both on the improvements in word error rate and how to speed up the recognizer with only minimal loss in recognition accuracy. Implementation details and experimental results are given for the VerbMobil task, a German spontaneous speech corpus. The 25.0% word error rate (WER) of our within-word baseline system was reduced to 21.4% with VTN and across-word models. Decreasing the real-time factor (RTF) by up to 85% resulted in only a small degradation in recognition performance of 2% relative on average.

引用

页码：1671 / 1674

页数：4

共 11 条

[1]

AUBERT X, 1999, P EUR C SPEECH COMM, P1559

[2] Dynamic programming search techniques for across-word modelling in speech recognition [J].

Beulen, K ;

Ortmanns, S ;

Elting, C .

ICASSP '99: 1999 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH, AND SIGNAL PROCESSING, PROCEEDINGS VOLS I-VI, 1999, :609-612

[3]

Bub T, 1996, ICSLP 96 - FOURTH INTERNATIONAL CONFERENCE ON SPOKEN LANGUAGE PROCESSING, PROCEEDINGS, VOLS 1-4, P2371, DOI 10.1109/ICSLP.1996.607285

[4]

KANTHAK S, 2000, UNPUB IEEE INT C AC

[5]

Lee L, 1996, INT CONF ACOUST SPEE, P353, DOI 10.1109/ICASSP.1996.541105

[6]

Ney H, 1998, INT CONF ACOUST SPEE, P853, DOI 10.1109/ICASSP.1998.675399

[7]

Ortmanns S, 1996, ICSLP 96 - FOURTH INTERNATIONAL CONFERENCE ON SPOKEN LANGUAGE PROCESSING, PROCEEDINGS, VOLS 1-4, P2091, DOI 10.1109/ICSLP.1996.607214

[8]

ORTMANNS S, 1999, P EUR C SPEECH COMM, P499

[9]

Ortmanns S., 1996, P CRIM FORWISS WORKS, P10

[10]

ORTMANNS S, 1997, P EUROSPEECH 97 EUR, P139

← 1 2 →