Spelling-Aware Word-Based End-to-End ASR

被引：1

作者：

Egorova, Ekaterina ^{[1
]}

Vydana, Hari Krishna ^{[1
]}

Burget, Lukas ^{[1
]}

Cernocky, Jan Honza ^{[1
]}

机构：

[1] Brno Univ Technol, Fac Informat Technol Speech FIT, CS-61090 Brno, Czech Republic

来源：

IEEE SIGNAL PROCESSING LETTERS | 2022年 / 29卷

基金：

欧盟地平线“2020”;

关键词：

Training; Vocabulary; Task analysis; Decoding; Predictive models; Training data; Recurrent neural networks; ASR; end-to-end; listen attend and spell architecture; OOV;

D O I：

10.1109/LSP.2022.3192199

中图分类号：

TM [电工技术]; TN [电子技术、通信技术];

学科分类号：

0808 ; 0809 ;

摘要：

We propose a new end-to-end architecture for automatic speech recognition that expands the "listen, attend and spell" (LAS) paradigm. While the main word-predicting network is trained to predict words, the secondary, speller network, is optimized to predict word spellings from inner representations of the main network (e.g. word embeddings or context vectors from the attention module). We show that this joint training improves the word error rate of a word-based system and enables solving additional tasks, such as out-of-vocabulary word detection and recovery. The tests are conducted on LibriSpeech dataset consisting of 1000 h of read speech.

引用

页码：1729 / 1733

页数：5

共 50 条

[1] END-TO-END SPEECH RECOGNITION WITH WORD-BASED RNN LANGUAGE MODELS
Hori, Takaaki
Cho, Jaejin
Watanabe, Shinji
[J]. 2018 IEEE WORKSHOP ON SPOKEN LANGUAGE TECHNOLOGY (SLT 2018), 2018, : 389 - 396
[2] ASR-AWARE END-TO-END NEURAL DIARIZATION
Khare, Aparna
Han, Eunjung
Yang, Yuguang
Stolcke, Andreas
[J]. 2022 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING (ICASSP), 2022, : 8092 - 8096
[3] SPEAKER AND LANGUAGE AWARE TRAINING FOR END-TO-END ASR
Bansal, Shubham
Malhotra, Karan
Ganapathy, Sriram
[J]. 2019 IEEE AUTOMATIC SPEECH RECOGNITION AND UNDERSTANDING WORKSHOP (ASRU 2019), 2019, : 494 - 501
[4] LEARNING WORD-LEVEL CONFIDENCE FOR SUBWORD END-TO-END ASR
Qiu, David
Li, Qiujia
He, Yanzhang
Zhang, Yu
Li, Bo
Cao, Liangliang
Prabhavalkar, Rohit
Bhatia, Deepti
Li, Wei
Hu, Ke
Sainath, Tara N.
McGraw, Ian
[J]. 2021 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING (ICASSP 2021), 2021, : 6393 - 6397
[5] Class LM and Word Mapping for Contextual Biasing in End-to-End ASR
Huang, Rongqing
Abdel-hamid, Ossama
Li, Xinwei
Evermann, Gunnar
[J]. INTERSPEECH 2020, 2020, : 4348 - 4351
[6] META-LEARNING FOR IMPROVING RARE WORD RECOGNITION IN END-TO-END ASR
Lux, Florian
Ngoc Thang Vu
[J]. 2021 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING (ICASSP 2021), 2021, : 5974 - 5978
[7] DOES SPEECH ENHANCEMENTWORK WITH END-TO-END ASR OBJECTIVES?: EXPERIMENTAL ANALYSIS OF MULTICHANNEL END-TO-END ASR
Ochiai, Tsubasa
Watanabe, Shinji
Katagiri, Shigeru
[J]. 2017 IEEE 27TH INTERNATIONAL WORKSHOP ON MACHINE LEARNING FOR SIGNAL PROCESSING, 2017,
[8] BOUNDARY AND CONTEXT AWARE TRAINING FOR CIF-BASED NON-AUTOREGRESSIVE END-TO-END ASR
Yu, Fan
Luo, Haoneng
Guo, Pengcheng
Bang, Yuhao
Yao, Zhuoyuan
Xie, Lei
Gao, Yingying
Hou, Leijing
Zhang, Shilei
[J]. 2021 IEEE AUTOMATIC SPEECH RECOGNITION AND UNDERSTANDING WORKSHOP (ASRU), 2021, : 328 - 334
[9] Auxiliary feature based adaptation of end-to-end ASR systems
Delcroix, Marc
Watanabe, Shinji
Ogawa, Atsunori
Karita, Shigeki
Nakatani, Tomohiro
[J]. 19TH ANNUAL CONFERENCE OF THE INTERNATIONAL SPEECH COMMUNICATION ASSOCIATION (INTERSPEECH 2018), VOLS 1-6: SPEECH RESEARCH FOR EMERGING MARKETS IN MULTILINGUAL SOCIETIES, 2018, : 2444 - 2448
[10] End-to-End Speech Emotion Recognition Combined with Acoustic-to-Word ASR Model
Feng, Han
Ueno, Sei
Kawahara, Tatsuya
[J]. INTERSPEECH 2020, 2020, : 501 - 505

← 1 2 3 4 5 →