ROBUST SPEECH RECOGNITION IN UNKNOWN REVERBERANT AND NOISY CONDITIONS

被引：0

作者：

Hsiao, Roger ^{[1
]}

Ma, Jeff ^{[1
]}

Hartmann, William ^{[1
]}

Karafiat, Martin ^{[2
]}

Grezl, Frantisek ^{[2
]}

Burget, Lukas ^{[2
]}

Szoke, Igor ^{[2
]}

Cernocky, Jan Honza ^{[2
]}

Watanabe, Shinji ^{[3
]}

Chen, Zhuo ^{[3
]}

Mallidi, Sri Harish ^{[4
]}

Hermansky, Hynek ^{[4
]}

Tsakalidis, Stavros ^{[1
]}

Schwartz, Richard ^{[1
]}

机构：

[1] Raytheon BBN Technol, Cambridge, MA 02138 USA

[2] Brno Univ Technol, Speech FIT & Ctr Excellence IT4I, CS-61090 Brno, Czech Republic

[3] Mitsubishi Elect Res Labs, Cambridge, MA USA

[4] Johns Hopkins Univ, Baltimore, MD USA

来源：

2015 IEEE WORKSHOP ON AUTOMATIC SPEECH RECOGNITION AND UNDERSTANDING (ASRU) | 2015年

关键词：

ASpIRE challenge; robust 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：

In this paper, we describe our work on the ASpIRE (Automatic Speech recognition In Reverberant Environments) challenge, which aims to assess the robustness of automatic speech recognition (ASR) systems. The main characteristic of the challenge is developing a high-performance system without access to matched training and development data. While the evaluation data are recorded with far-field microphones in noisy and reverberant rooms, the training data are telephone speech and close talking. Our approach to this challenge includes speech enhancement, neural network methods and acoustic model adaptation, We show that these techniques can successfully alleviate the performance degradation due to noisy audio and data mismatch.

引用

下载

页码：533 / 538

页数：6

共 50 条

[1] Techniques for robust speech recognition in noisy and reverberant conditions
Brown, GJ
Palomäki, KJ
SPEECH SEPARATION BY HUMANS AND MACHINES, 2005, : 213 - 220
[2] OPTIMIZING SPECTRAL SUBTRACTION AND WIENER FILTERING FOR ROBUST SPEECH RECOGNITION IN REVERBERANT AND NOISY CONDITIONS
Gomez, Randy
Kawahara, Tatsuya
2010 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH, AND SIGNAL PROCESSING, 2010, : 4566 - 4569
[3] Speech Enhancement and Recognition of Compressed Speech Signal in Noisy Reverberant Conditions
Suman, Maloji
Khan, Habibulla
Latha, M. Madhavi
Kumari, Devarakonda Aruna
PROCEEDINGS OF THE INTERNATIONAL CONFERENCE ON INFORMATION SYSTEMS DESIGN AND INTELLIGENT APPLICATIONS 2012 (INDIA 2012), 2012, 132 : 379 - +
[4] Feature Transformations for Robust Speech Recognition in Reverberant Conditions
Yuliani, Asri R.
Sustika, Rika
Yuwana, Raden S.
Pardede, Hilman F.
2017 INTERNATIONAL CONFERENCE ON COMPUTER, CONTROL, INFORMATICS AND ITS APPLICATIONS (IC3INA), 2017, : 57 - 62
[5] DISTANT SPEECH RECOGNITION IN REVERBERANT NOISY CONDITIONS EMPLOYING A MICROPHONE ARRAY
Morales-Cordovilla, Juan A.
Hagmueller, Martin
Pessentheiner, Hannes
Kubin, Gernot
2014 PROCEEDINGS OF THE 22ND EUROPEAN SIGNAL PROCESSING CONFERENCE (EUSIPCO), 2014, : 2380 - 2384
[6] ROBUST RECOGNITION OF REVERBERANT AND NOISY SPEECH USING COHERENCE-BASED PROCESSING
Menon, Anjali
Kim, Chanwoo
Stern, Richard M.
2019 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING (ICASSP), 2019, : 6775 - 6779
[7] Speech Emotion Recognition in Noisy and Reverberant Environments
Heracleous, Panikos
Yasuda, Keiji
Sugaya, Fumiaki
Yoneyama, Akio
Hashimoto, Masayuki
2017 SEVENTH INTERNATIONAL CONFERENCE ON AFFECTIVE COMPUTING AND INTELLIGENT INTERACTION (ACII), 2017, : 262 - 266
[8] Speech Intelligibility Enhancement in Noisy Reverberant Conditions
Li, Junfeng
Xia, Risheng
Fang, Qiang
Li, Aijun
Yan, Yonghong
2016 10TH INTERNATIONAL SYMPOSIUM ON CHINESE SPOKEN LANGUAGE PROCESSING (ISCSLP), 2016,
[9] AMPLITUDE MODULATION SPECTROGRAM BASED FEATURES FOR ROBUST SPEECH RECOGNITION IN NOISY AND REVERBERANT ENVIRONMENTS
Moritz, Niko
Anemueller, Joern
Kollmeier, Birger
2011 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH, AND SIGNAL PROCESSING, 2011, : 5492 - 5495
[10] Robust Speaker Identification in Noisy and Reverberant Conditions
Zhao, Xiaojia
Wang, Yuxuan
Wang, DeLiang
IEEE-ACM TRANSACTIONS ON AUDIO SPEECH AND LANGUAGE PROCESSING, 2014, 22 (04) : 836 - 845

← 1 2 3 4 5 →