Computer-assisted transcription of speech based on confusion network reordering

被引：0

作者：

Laurent, Antoine ^{[1
]}

Meignier, Sylvain ^{[1
]}

Merlin, Teva ^{[1
]}

Deleglise, Paul ^{[1
]}

机构：

[1] Univ Maine, LIUM, Res Ctr Comp Sci, F-72017 Le Mans, France

来源：

2011 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH, AND SIGNAL PROCESSING | 2011年

关键词：

Speech recognition; Automatic correction; Cache models; Confusion network; TRANSLATION; RECOGNITION;

D O I：

暂无

中图分类号：

O42 [声学];

学科分类号：

070206 ; 082403 ;

摘要：

Large vocabulary automatic speech recognition (ASR) technologies perform well in known and controlled contexts. In less controlled conditions, however, human review is often necessary to check and correct the results of such systems in order to ensure that the output of ASR will be understandable. We propose a method for computer-assisted transcription of speech, based on automatic reordering confusion networks. Our method will be evaluated in terms of KSR (Keystroke Saving Rate) and WSR (Word Stroke Ratio). It allows to significantly reduce the number of actions needed to correct ASR outputs. WSR computed before and after every network reordering shows a gain of about 17.7% (3.4 points).

引用

页码：4884 / 4887

页数：4

共 16 条

[1]

Amengual J. C., 2000, MACHINE TRANSLATION, V14, P941

[2]

Bazillon T, 2008, TRAIT AUTOM LANG, V49, P47

[3]

Cardinal P., 2007, ACL, P113

[4] Pattern recognition approaches for speech-to-speech translation [J].

Casacuberta, F ;

Vidal, E ;

Sanchis, A ;

Vilar, JM .

CYBERNETICS AND SYSTEMS, 2004, 35 (01) :3-17

[5]

Civera J, 2004, LECT NOTES COMPUT SC, V3138, P207

[6]

Civera J., 2005, FSMNLP, V4002, P32

[7]

Clarkson P., 1997, ICASSP MUN, V2, P799

[8]

Cubel E, 2004, FR ART INT, V110, P586

[9]

Deleglise P., 2009, INTERSPEECH, P2123

[10]

FOSTER G, 2002, THESIS U MONTREAL CA

← 1 2 →