INCORPORATING MASK MODELLING FOR NOISE-ROBUST AUTOMATIC SPEECH RECOGNITION

被引：2

作者：

Koekueer, Muenevver ^{[1
]}

Jancovic, Peter ^{[1
]}

机构：

[1] Univ Birmingham, Sch Elect Elect & Comp Engn, Birmingham, W Midlands, England

来源：

2009 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH, AND SIGNAL PROCESSING, VOLS 1- 8, PROCEEDINGS | 2009年

关键词：

automatic speech recognition; mask modelling; noise robustness; missing-feature theory;

D O I：

10.1109/ICASSP.2009.4960487

中图分类号：

O42 [声学];

学科分类号：

070206 ; 082403 ;

摘要：

In this paper we investigate an incorporation of mask modelling into an HMM-based ASR system. The mask model is estimated for each HMM state and mixture by using a separate Viterbi-style training procedure and it expresses which regions of the spectrum are expected to be uncorrupted by noise for the HMM state. Experimental evaluation is performed on noisy speech data from the Aurora 2 database. Significant performance improvements are achieved when the mask modelling is incorporated within the standard model and two models that had already compensated for the effect of the noise.

引用

页码：3929 / 3932

页数：4

共 50 条

[41] A speech emphasis method for noise-robust speech recognition by using repetitive phrase
Hirai, Takanori
Kuroiwa, Shingo
Tsuge, Satoru
Ren, Fuji
Fattah, Mohamed Abdel
[J]. 2006 10TH INTERNATIONAL CONFERENCE ON COMMUNICATION TECHNOLOGY, VOLS 1 AND 2, PROCEEDINGS, 2006, : 1269 - +
[42] Employing Robust Principal Component Analysis for Noise-Robust Speech Feature Extraction in Automatic Speech Recognition with the Structure of a Deep Neural Network
Hung, Jeih-weih
Lin, Jung-Shan
Wu, Po-Jen
[J]. APPLIED SYSTEM INNOVATION, 2018, 1 (03) : 1 - 14
[43] Improved model parameter compensation methods for noise-robust speech recognition
Chang, YH
Chung, YJ
Park, SU
[J]. PROCEEDINGS OF THE 1998 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING, VOLS 1-6, 1998, : 561 - 564
[44] GAUSSIAN POWER FLOW ORIENTATION COEFFICIENTS FOR NOISE-ROBUST SPEECH RECOGNITION
Gerazov, Branislav
Ivanovski, Zoran
[J]. 2014 PROCEEDINGS OF THE 22ND EUROPEAN SIGNAL PROCESSING CONFERENCE (EUSIPCO), 2014, : 1467 - 1471
[45] Probabilistic vector mapping with trajectory information for noise-robust speech recognition
Kim, DY
Un, CK
[J]. ELECTRONICS LETTERS, 1996, 32 (17) : 1550 - 1551
[46] Modeling sub-band correlation for noise-robust speech recognition
McAuley, J
Ming, J
Hanna, P
Stewart, D
[J]. 2004 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH, AND SIGNAL PROCESSING, VOL I, PROCEEDINGS: SPEECH PROCESSING, 2004, : 1017 - 1020
[47] Noise-robust speech recognition by discriminative adaptation in parallel model combination
Chung, YJ
[J]. ELECTRONICS LETTERS, 2000, 36 (04) : 370 - 371
[48] A Noise-Robust Speech Recognition System Based on Wavelet Neural Network
Wang, Yiping
Zhao, Zhefeng
[J]. ARTIFICIAL INTELLIGENCE AND COMPUTATIONAL INTELLIGENCE, PT III, 2011, 7004 : 392 - 397
[49] Noise-robust cellular phone speech recognition using CODEC-adapted speech and noise models
Kato, T
Naito, M
Shimizu, T
[J]. 2002 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH, AND SIGNAL PROCESSING, VOLS I-IV, PROCEEDINGS, 2002, : 285 - 288
[50] Noise-robust Attention Learning for End-to-End Speech Recognition
Higuchi, Yosuke
Tawara, Naohiro
Ogawa, Atsunori
Iwata, Tomoharu
Kobayashi, Tetsunori
Ogawa, Tetsuji
[J]. 28TH EUROPEAN SIGNAL PROCESSING CONFERENCE (EUSIPCO 2020), 2021, : 311 - 315

← 1 2 3 4 5 →