Integrating Knowledge Into End-to-End Speech Recognition From External Text-Only Data

doi:10.1109/TASLP.2021.3066274

	Integrating Knowledge Into End-to-End Speech Recognition From External Text-Only Data
	Bai, Ye1 ; Yi, Jiangyan2 ; Tao, Jianhua2,3 ; Wen, Zhengqi2 ; Tian, Zhengkun1 ; Zhang, Shuai1
发表期刊	IEEE-ACM TRANSACTIONS ON AUDIO SPEECH AND LANGUAGE PROCESSING
ISSN	2329-9290
	2021
卷号	29 页码:1340-1351
通讯作者	Yi, Jiangyan(jiangyan.yi@nlpr.ia.ac.cn) ; Tao, Jianhua(jhtao@nlpr.ia.ac.cn)
摘要	Attention-based encoder-decoder (AED) models have achieved promising performance in speech recognition. However, because of the end-to-end training, an AED model is usually trained with speech-text paired data. It is challenging to incorporate external text-only data into AED models. Another issue of the AED model is that it does not use the right context of a text token while predicting the token. To alleviate the above two issues, we propose a unified method called LST (Learn Spelling from Teachers) to integrate knowledge into an AED model from the external text-only data and leverage the whole context in a sentence. The method is divided into two stages. First, in the representation stage, a language model is trained on the text. It can be seen as that the knowledge in the text is compressed into the LM. Then, at the transferring stage, the knowledge is transferred to the AED model via teacher-student learning. To further use the whole context of the text sentence, we propose an LM called causal cloze completer (COR), which estimates the probability of a token, given both the left context and the right context of it. Therefore, with LST training, the AED model can leverage the whole context in the sentence. Different from fusion based methods, which use LM during decoding, the proposed method does not increase any extra complexity at the inference stage. We conduct experiments on two scales of public Chinese datasets AISHELL-1 and AISHELL-2. The experimental results demonstrate the effectiveness of leveraging external text-only data and the whole context in a sentence with our proposed method, compared with baseline hybrid systems and AED model based systems.
关键词	End-to-End language modeling speech recognition teacher-student learning transfer learning
DOI	10.1109/TASLP.2021.3066274
关键词[WOS]	NETWORK LANGUAGE MODELS
收录类别	SCI
语种	英语
资助项目	National Key Research and Development Plan of China[2018YFB1005003] ; National Natural Science Foundation of China (NSFC)[61831022] ; National Natural Science Foundation of China (NSFC)[61901473] ; National Natural Science Foundation of China (NSFC)[61771472] ; National Natural Science Foundation of China (NSFC)[61773379] ; National Natural Science Foundation of China (NSFC)[173211KYSB20190049]
项目资助者	National Key Research and Development Plan of China ; National Natural Science Foundation of China (NSFC)
WOS研究方向	Acoustics ; Engineering
WOS类目	Acoustics ; Engineering, Electrical & Electronic
WOS记录号	WOS:000640712800001
出版者	IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
七大方向——子方向分类	语音识别与合成
引用统计	被引频次：4[WOS] [WOS记录] [WOS相关记录]
文献类型	期刊论文
条目标识符	http://ir.ia.ac.cn/handle/173211/44504
专题	多模态人工智能系统全国重点实验室_智能交互
通讯作者	Yi, Jiangyan; Tao, Jianhua
作者单位	1.Univ Chinese Acad Sci, Beijing 100190, Peoples R China 2.Chinese Acad Sci, Inst Automat, NLPR, Beijing 100190, Peoples R China 3.CAS Ctr Excellence Brain Sci & Intelligence Techn, Beijing 100190, Peoples R China
通讯作者单位	模式识别国家重点实验室
推荐引用方式 GB/T 7714	Bai, Ye,Yi, Jiangyan,Tao, Jianhua,et al. Integrating Knowledge Into End-to-End Speech Recognition From External Text-Only Data[J]. IEEE-ACM TRANSACTIONS ON AUDIO SPEECH AND LANGUAGE PROCESSING,2021,29:1340-1351.
APA	Bai, Ye,Yi, Jiangyan,Tao, Jianhua,Wen, Zhengqi,Tian, Zhengkun,&Zhang, Shuai.(2021).Integrating Knowledge Into End-to-End Speech Recognition From External Text-Only Data.IEEE-ACM TRANSACTIONS ON AUDIO SPEECH AND LANGUAGE PROCESSING,29,1340-1351.
MLA	Bai, Ye,et al."Integrating Knowledge Into End-to-End Speech Recognition From External Text-Only Data".IEEE-ACM TRANSACTIONS ON AUDIO SPEECH AND LANGUAGE PROCESSING 29(2021):1340-1351.