Prosodic Features for a Maximum Entropy Language Model

被引：0

作者：

Chan, Oscar ^{[1
]}

Togneri, Roberto ^{[1
]}

机构：

[1] Univ Western Australia, Sch Elect Elect & Comp Engn, Nedlands, WA 6009, Australia

来源：

INTERSPEECH 2006 AND 9TH INTERNATIONAL CONFERENCE ON SPOKEN LANGUAGE PROCESSING, VOLS 1-5 | 2006年

关键词：

language modelling; prosody; speech recognition;

D O I：

暂无

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

This paper presents an approach for incorporating prosodic knowledge into the language modelling component of a speech recogniser. We formulate features for a maximum entropy language model which capture various aspects of the relationships between prosody, syntax and the spoken word sequence. Maximum entropy is a powerful modelling technique, and well suited to modelling prosodic information. Tests conducted on the Boston University Radio Speech Corpus using this model showed improvements in perplexity, and n-best rescoring results also demonstrated small but statistically significant gains.

引用

页码：1858 / 1861

页数：4

共 50 条

[31] Investigating linguistic knowledge in a maximum entropy token-based language model
Cui, Jia
Su, Yi
Hall, Keith
Jelinek, Frederick
2007 IEEE WORKSHOP ON AUTOMATIC SPEECH RECOGNITION AND UNDERSTANDING, VOLS 1 AND 2, 2007, : 171 - 176
[32] Efficient Estimation of Maximum Entropy Language Models with N-gram features: an SRILM extension
Alumaee, Tanel
Kurimo, Mikko
11TH ANNUAL CONFERENCE OF THE INTERNATIONAL SPEECH COMMUNICATION ASSOCIATION 2010 (INTERSPEECH 2010), VOLS 3 AND 4, 2010, : 1820 - +
[33] PROSODIC ATTRIBUTE MODEL FOR SPOKEN LANGUAGE IDENTIFICATION
Ng, Raymond W. M.
Leung, Cheung-Chi
Lee, Tan
Ma, Bin
Li, Haizhou
2010 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH, AND SIGNAL PROCESSING, 2010, : 5022 - 5025
[34] Prosodic features of familial language impairment: Constraints on stress assignment
Piggott, GL
Robb, MK
FOLIA PHONIATRICA ET LOGOPAEDICA, 1999, 51 (1-2) : 55 - 69
[35] Poetry Generative Model Incorporating Prosodic Features
Wu, Lindong
He, Xiangzhen
Wan, Fucheng
Computer Engineering and Applications, 2024, 60 (13) : 162 - 170
[36] ACQUISITION OF PROSODIC AND ARTICULATORY FEATURES IN ADULT LANGUAGE-LEARNING
NEUFELD, GG
CANADIAN MODERN LANGUAGE REVIEW-REVUE CANADIENNE DES LANGUES VIVANTES, 1978, 34 (02): : 163 - 174
[37] Integrating acoustic, prosodic and phonotactic features for spoken language identification
Tong, Rong
Ma, Bin
Zhu, Donglai
Li, Haizhou
Chng, Eng Siong
2006 IEEE International Conference on Acoustics, Speech and Signal Processing, Vols 1-13, 2006, : 205 - 208
[38] Language Classification Using Prosodic Features: Comparing Intensity and Pitch
Zulu, Peleira Nicholas
2013 Pan African International Conference on Information Science, Computing and Telecommunications (PACT), 2013, : 116 - 121
[39] Maximum entropy language modeling and the smoothing problem
Martin, SC
Ney, H
Hamacher, C
IEEE TRANSACTIONS ON SPEECH AND AUDIO PROCESSING, 2000, 8 (05): : 626 - 632
[40] Smoothing methods in maximum entropy language modeling
Martin, SC
Ney, H
Zaplo, J
ICASSP '99: 1999 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH, AND SIGNAL PROCESSING, PROCEEDINGS VOLS I-VI, 1999, : 545 - 548

← 1 2 3 4 5 →