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

[21] Robust Speech Recognition for Similar Japanese Pronunciation Phrases Under Noisy Conditions
Mufungulwa, George
Tsutsui, Hiroshi
Miyanaga, Yoshikazu
Abe, Shin-ichi
Ochi, Mitsuru
2017 INTERNATIONAL SYMPOSIUM ON SIGNALS, CIRCUITS AND SYSTEMS (ISSCS), 2017,
[22] MAXIMUM LIKELIHOOD PSD ESTIMATION FOR SPEECH ENHANCEMENT IN REVERBERANT AND NOISY CONDITIONS
Kuklasinski, Adam
Doclo, Simon
Jensen, Jesper
2016 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING PROCEEDINGS, 2016, : 599 - 603
[23] Contribution of modulation spectral features for cross-lingual speech emotion recognition under noisy reverberant conditions
Guo, Taiyang
Li, Sixia
Kidani, Shunsuke
Okada, Shogo
Unoki, Masashi
2023 ASIA PACIFIC SIGNAL AND INFORMATION PROCESSING ASSOCIATION ANNUAL SUMMIT AND CONFERENCE, APSIPA ASC, 2023, : 2221 - 2227
[24] Experimental study of robust acoustic beamforming for speech acquisition in reverberant and noisy environments
Zhao, Yingke
Jensen, Jesper Rindom
Jensen, Tobias Lindstrom
Chen, Jingdong
Christensen, Mads Graesboll
APPLIED ACOUSTICS, 2020, 170
[25] Robust speaker recognition in noisy conditions
Ming, Ji
Hazen, Timothy J.
Glass, James R.
Reynolds, Douglas A.
IEEE TRANSACTIONS ON AUDIO SPEECH AND LANGUAGE PROCESSING, 2007, 15 (05): : 1711 - 1723
[26] IMPULSE RESPONSE ESTIMATION FOR ROBUST SPEECH RECOGNITION IN A REVERBERANT ENVIRONMENT
Ravanelli, Mirco
Sosi, Alessandro
Svaizer, Piergiorgio
Omologo, Maurizio
2012 PROCEEDINGS OF THE 20TH EUROPEAN SIGNAL PROCESSING CONFERENCE (EUSIPCO), 2012, : 1668 - 1672
[27] An efficient joint training model for monaural noisy-reverberant speech recognition
Lian, Xiaoyu
Xia, Nan
Dai, Gaole
Yang, Hongqin
Applied Acoustics, 2025, 228
[28] Improving Robustness of Speaker Recognition in Noisy and Reverberant Conditions via Training
Al-Noori, Ahmed H.
Al-Karawi, Khamis A.
Li, Francis F.
2015 European Intelligence and Security Informatics Conference (EISIC), 2015, : 180 - 180
[29] Speech Enhancement of Noisy and Reverberant Speech for Text-to-Speech
Valentini-Botinhao, Cassia
Yamagishi, Junichi
IEEE-ACM TRANSACTIONS ON AUDIO SPEECH AND LANGUAGE PROCESSING, 2018, 26 (08) : 1420 - 1433
[30] SPEECH RECOGNITION IN UNSEEN AND NOISY CHANNEL CONDITIONS
Mitra, Vikramjit
Franco, Horacio
Bartels, Chris
van Hout, Julien
Graciarena, Martin
Vergyri, Dimitra
2017 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING (ICASSP), 2017, : 5215 - 5219

← 1 2 3 4 5 →