Institutional Repository of Chinese Acad Sci, Inst Automat, Natl Lab Pattern Recognit, Beijing 100190, Peoples R China
| 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
| |
| Source Publication | IEEE-ACM TRANSACTIONS ON AUDIO SPEECH AND LANGUAGE PROCESSING
 |
| ISSN | 2329-9290 |
| 2021 | |
| Volume | 29Pages:1340-1351 |
| Corresponding Author | Yi, Jiangyan(jiangyan.yi@nlpr.ia.ac.cn) ; Tao, Jianhua(jhtao@nlpr.ia.ac.cn) |
| Abstract | 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. |
| Keyword | End-to-End language modeling speech recognition teacher-student learning transfer learning |
| DOI | 10.1109/TASLP.2021.3066274 |
| WOS Keyword | NETWORK LANGUAGE MODELS |
| Indexed By | SCI |
| Language | 英语 |
| Funding Project | 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] |
| Funding Organization | National Key Research and Development Plan of China ; National Natural Science Foundation of China (NSFC) |
| WOS Research Area | Acoustics ; Engineering |
| WOS Subject | Acoustics ; Engineering, Electrical & Electronic |
| WOS ID | WOS:000640712800001 |
| Publisher | IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC |
| Sub direction classification | 语音识别与合成 |
| Citation statistics | |
| Document Type | 期刊论文 |
| Identifier | http://ir.ia.ac.cn/handle/173211/44504 |
| Collection | 模式识别国家重点实验室_智能交互 |
| Corresponding Author | Yi, Jiangyan; Tao, Jianhua |
| Affiliation | 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 |
| Corresponding Author Affilication | Chinese Acad Sci, Inst Automat, Natl Lab Pattern Recognit, Beijing 100190, Peoples R China |
| Recommended Citation 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. |
| Files in This Item: | There are no files associated with this item. | |||||
Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.
Edit Comment