Train from scratch: Single-stage joint training of speech separation and recognition
文献类型:期刊论文
作者 | Shi, Jing3; Chang, Xuankai2; Watanabe, Shinji2; Xu, Bo1,3 |
刊名 | COMPUTER SPEECH AND LANGUAGE |
出版日期 | 2022-11-01 |
卷号 | 76页码:15 |
ISSN号 | 0885-2308 |
关键词 | Cocktail party problem Speech separation Multi-speaker speech recognition End-to-end Joint-training |
DOI | 10.1016/j.csl.2022.101387 |
通讯作者 | Watanabe, Shinji(shinjiw@ieee.org) |
英文摘要 | Multi-speaker speech separation and recognition gains much attention in the speech community recently. Previously, most studies train the front-end separation module and back-end recognition module individually. The two modules after training are combined together either with a hybrid structure or by fine-tuning the resulting model. In this work, we present a unified and flexible multi-speaker end-to-end ASR model. In contrast to previous studies, our proposed model is trained from scratch with a complete single stage, rather than multiple training stages based on pre-training and the following fine-tuning. Our model can deal with either single channel or multi-channel speech input. Moreover, the proposed model can be trained with or without the clean source speech references. We evaluate the proposed model on the WSJ02mix dataset in both single-channel and spatialized multi-channel conditions. The experiments demonstrate that the proposed methods can improve the performance of the end-to-end model in recognizing the separated streams without much degradation in speech separation, achieving a new state-of-the-art in the WSJ0-2mix dataset. Moreover, we systematically assess the impact of various features for the success of the joint-training model and will release all our codes, which may provide a new guidance for the integration of front-end and back-end towards complex auditory scenes. |
WOS关键词 | DOMAIN AUDIO SEPARATION ; NEURAL-NETWORKS ; END |
WOS研究方向 | Computer Science |
语种 | 英语 |
出版者 | ACADEMIC PRESS LTD- ELSEVIER SCIENCE LTD |
WOS记录号 | WOS:000798734700002 |
源URL | [http://ir.ia.ac.cn/handle/173211/49506] |
专题 | 数字内容技术与服务研究中心_听觉模型与认知计算 |
通讯作者 | Watanabe, Shinji |
作者单位 | 1.Univ Chinese Acad Sci, Beijing, Peoples R China 2.Johns Hopkins Univ, Ctr Language & Speech Proc, Baltimore, MD 21218 USA 3.Chinese Acad Sci CASIA, Inst Automat, Beijing, Peoples R China |
推荐引用方式 GB/T 7714 | Shi, Jing,Chang, Xuankai,Watanabe, Shinji,et al. Train from scratch: Single-stage joint training of speech separation and recognition[J]. COMPUTER SPEECH AND LANGUAGE,2022,76:15. |
APA | Shi, Jing,Chang, Xuankai,Watanabe, Shinji,&Xu, Bo.(2022).Train from scratch: Single-stage joint training of speech separation and recognition.COMPUTER SPEECH AND LANGUAGE,76,15. |
MLA | Shi, Jing,et al."Train from scratch: Single-stage joint training of speech separation and recognition".COMPUTER SPEECH AND LANGUAGE 76(2022):15. |
入库方式: OAI收割
来源:自动化研究所
浏览0
下载0
收藏0
其他版本
除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。