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

[21] METHOD FOR RECORDING AND ANALYZING PROSODIC FEATURES OF LANGUAGE
SILVERMAN, SH
MODERN LANGUAGE JOURNAL, 1969, 53 (04): : 250 - 254
[22] Active learning for prediction of prosodic word boundaries in Chinese TTS using Maximum Entropy Markov model
Zhao, Ziping
Ma, Xirong
Journal of Software, 2013, 8 (12) : 3222 - 3228
[23] Combined maximum entropy language model using different feature sets
Zhuang, L
Zhu, X
ELECTRONICS LETTERS, 2005, 41 (02) : 106 - 107
[24] Word Alignment Model Based on Maximum Entropy in Foreign Language Translation
Jun, Chen
2020 5TH INTERNATIONAL CONFERENCE ON SMART GRID AND ELECTRICAL AUTOMATION (ICSGEA 2020), 2020, : 635 - 638
[25] ENTROPY-BASED ANALYSIS OF THE PROSODIC FEATURES OF CHINESE DIALECTS
Ng, Raymond W. M.
Lee, Tan
2008 6TH INTERNATIONAL SYMPOSIUM ON CHINESE SPOKEN LANGUAGE PROCESSING, PROCEEDINGS, 2008, : 65 - 68
[26] Language Identification System using MFCC and Prosodic Features
Bhattacharjee, Utpal
KshirodSarmah
2013 INTERNATIONAL CONFERENCE ON INTELLIGENT SYSTEMS AND SIGNAL PROCESSING (ISSP), 2013, : 194 - 197
[27] Salient prosodic features on judgments of second language accent
Northern Arizona University, United States
Proc. Int. Conf. Speech Prosody,
[28] Detection of Questions in Berber Language Using Prosodic Features
Ramzi, Halimouche
Hocine, Teffahi
Leila, Falek
2014 INTERNATIONAL CONFERENCE ON MULTIMEDIA COMPUTING AND SYSTEMS (ICMCS), 2014, : 197 - 200
[29] Extraction and representation of prosodic features for language and speaker recognition
Mary, Leena
Yegnanarayana, B.
SPEECH COMMUNICATION, 2008, 50 (10) : 782 - 796
[30] Prediction of Prosodic Word Boundaries in Chinese TTS Based on Maximum Entropy Markov Model and Transformation Based Learning
Zhao, Ziping
Ma, Xirong
PROCEEDINGS OF THE 2012 EIGHTH INTERNATIONAL CONFERENCE ON COMPUTATIONAL INTELLIGENCE AND SECURITY (CIS 2012), 2012, : 258 - 261

← 1 2 3 4 5 →