MLP BASED PHONEME DETECTORS FOR AUTOMATIC SPEECH RECOGNITION

被引：0

作者：

Thomas, Samuel ^{[1
]}

Patrick Nguyen

Zweig, Geoffrey

Hermansky, Hynek ^{[1
]}

机构：

[1] Johns Hopkins Univ, Baltimore, MD 21218 USA

来源：

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

关键词：

Phoneme Posteriors; Multi-layer Perceptrons; Segmental Conditional Random Fields;

D O I：

暂无

中图分类号：

O42 [声学];

学科分类号：

070206 ; 082403 ;

摘要：

Phoneme posterior probabilities estimated using Multi-Layer Perceptrons (MLPs) are extensively used both as acoustic scores and features for speech recognition. In this paper we explore a different application of these posteriors - as phonetic event detectors for speech recognition. We show how these detectors can be built to reliably capture phonetic events in the acoustic signal by integrating both acoustic and phonetic information about sound classes. These event detectors are used along with Segmental Conditional Random Fields (SCRFs) to improve the performance of speech recognition systems on the Broadcast News task.

引用

页码：5024 / 5027

页数：4

共 50 条

[41] Conversion from Phoneme Based to Grapheme Based Acoustic Models for Speech Recognition
Zgank, Andrej
Kacic, Zdravko
[J]. INTERSPEECH 2006 AND 9TH INTERNATIONAL CONFERENCE ON SPOKEN LANGUAGE PROCESSING, VOLS 1-5, 2006, : 1587 - 1590
[42] SPEECH RECOGNITION BASED ON TOP-DOWN AND BOTTOM-UP PHONEME RECOGNITION
MATSUNAGA, S
SHIKANO, K
[J]. REVIEW OF THE ELECTRICAL COMMUNICATIONS LABORATORIES, 1986, 34 (03): : 349 - 356
[43] Data Selection Based on Phoneme Affinity Matrix for Electrolarynx Speech Recognition
Hsieh, I-Ting
Wu, Chung-Hsien
Tsai, Shu-Wei
[J]. 2023 ASIA PACIFIC SIGNAL AND INFORMATION PROCESSING ASSOCIATION ANNUAL SUMMIT AND CONFERENCE, APSIPA ASC, 2023, : 2196 - 2202
[44] Emotional feature extraction based on phoneme information for speech emotion recognition
Hyun, Kyang Hak
Kim, Eun Ho
Kwak, Yoon Keun
[J]. 2007 RO-MAN: 16TH IEEE INTERNATIONAL SYMPOSIUM ON ROBOT AND HUMAN INTERACTIVE COMMUNICATION, VOLS 1-3, 2007, : 797 - +
[45] Automatic phoneme recognition in Venezuelan continuous speech based on hidden Markov models and artificial neural networks hybrid systems
Jabbour, Georges
Maldonado, Jose Luciano
[J]. CIENCIA E INGENIERIA, 2014, 35 (01): : 29 - 38
[46] A STOCHASTIC SEGMENT MODEL FOR PHONEME-BASED CONTINUOUS SPEECH RECOGNITION
OSTENDORF, M
ROUKOS, S
[J]. IEEE TRANSACTIONS ON ACOUSTICS SPEECH AND SIGNAL PROCESSING, 1989, 37 (12): : 1857 - 1869
[47] Feature Selection Using Game Theory for Phoneme Based Speech Recognition
Rekha, J. Ujwala
Chatrapati, K. Shahu
Babu, A. Vinaya
[J]. 2014 INTERNATIONAL CONFERENCE ON CONTEMPORARY COMPUTING AND INFORMATICS (IC3I), 2014, : 962 - 966
[48] Minimum Phoneme Error based filter bank analysis for speech recognition
Huang, Hao
Zhu, Jie
[J]. 2006 IEEE INTERNATIONAL CONFERENCE ON MULTIMEDIA AND EXPO - ICME 2006, VOLS 1-5, PROCEEDINGS, 2006, : 1081 - +
[49] CONTINUOUS PHONEME RECOGNITION IN CUED SPEECH FOR FRENCH
Heracleous, Panikos
Beautemps, Denis
Hagita, Norihiro
[J]. 2012 PROCEEDINGS OF THE 20TH EUROPEAN SIGNAL PROCESSING CONFERENCE (EUSIPCO), 2012, : 2090 - 2093
[50] Phoneme recognition using speech image (spectrogram)
Ahmadi, M
Bailey, NJ
Hoyle, BS
[J]. ICSP '96 - 1996 3RD INTERNATIONAL CONFERENCE ON SIGNAL PROCESSING, PROCEEDINGS, VOLS I AND II, 1996, : 675 - 677

← 1 2 3 4 5 →