CampNet: Context-Aware Mask Prediction for End-to-End Text-Based Speech Editing

doi:10.1109/TASLP.2022.3190717

	CampNet: Context-Aware Mask Prediction for End-to-End Text-Based Speech Editing
	Wang, Tao1,2 ; Yi, Jiangyan1 ; Fu, Ruibo1 ; Tao, Jianhua1 ; Wen, Zhengqi1
发表期刊	IEEE-ACM TRANSACTIONS ON AUDIO SPEECH AND LANGUAGE PROCESSING
ISSN	2329-9290
	2022
卷号	30 页码:2241-2254
通讯作者	Yi, Jiangyan(jiangyan.yi@nlpr.ia.ac.cn) ; Fu, Ruibo(ruibo.fu@nlpr.ia.ac.cn) ; Tao, Jianhua(jhtao@nlpr.ia.ac.cn)
摘要	The text-based speech editor allows the editing of speech through intuitive cutting, copying, and pasting operations to speed up the process of editing speech. However, the major drawback of current systems is that edited speech often sounds unnatural due to cut-copy-paste operation. In addition, it is not obvious how to synthesize records according to a new word not appearing in the transcript. This paper first proposes a novel end-to-end text-based speech editing method called context-aware mask prediction network (CampNet), which can solve unnatural prosody in the edited region and synthesize the speech corresponding to the unseen words in the transcript. Secondly, to cover various situations of text-based speech editing, we design three text-based operations based on CampNet: deletion, insertion, and replacement. Thirdly, to synthesize the speech corresponding to long text, a word-level autoregressive generation method is proposed. Fourthly, we propose a speaker adaptation method using only one sentence for CampNet and explore the ability of few-shot learning based on CampNet, which provides a new idea for speech forgery tasks. The subjective and objective experiments on VCTK and LibriTTS datasets(1) (1) Examples of generated speech can be found at https://hairuo55.github.io/CampNet show that the speech editing results based on CampNet are better than TTS technology, manual editing, and VoCo method. We also conduct detailed ablation experiments to explore the effect of the CampNet structure on its performance. Finally, the experiment shows that speaker adaptation with only one sentence can further improve the naturalness of speech editing for one-shot learning.
关键词	Speech processing Decoding Predictive models Acoustics Transfer learning Training Task analysis Coarse-to-fine decoding mask prediction one-shot learning text-based speech editing text-to-speech
DOI	10.1109/TASLP.2022.3190717
关键词[WOS]	VOCODER ; GENERATION ; STRAIGHT ; NETWORKS
收录类别	SCI
语种	英语
资助项目	Key Research Project of China[2019KD0AD01] ; National Natural Science Foundation of China[61901473] ; National Natural Science Foundation of China[62101553] ; National Natural Science Foundation of China[61831022] ; Huawei Noah's Ark Lab
项目资助者	Key Research Project of China ; National Natural Science Foundation of China ; Huawei Noah's Ark Lab
WOS研究方向	Acoustics ; Engineering
WOS类目	Acoustics ; Engineering, Electrical & Electronic
WOS记录号	WOS:000831126700002
出版者	IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
引用统计	被引频次：2[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/173211/49768
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; Fu, Ruibo; Tao, Jianhua
作者单位	1.Chinese Acad Sci, Inst Automat, Natl Lab Pattern Recognit, Beijing 100190, Peoples R China 2.Univ Chinese Acad Sci, Sch Artificial Intelligence, Beijing 100190, Peoples R China
第一作者单位	模式识别国家重点实验室
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	Wang, Tao,Yi, Jiangyan,Fu, Ruibo,et al. CampNet: Context-Aware Mask Prediction for End-to-End Text-Based Speech Editing[J]. IEEE-ACM TRANSACTIONS ON AUDIO SPEECH AND LANGUAGE PROCESSING,2022,30:2241-2254.
APA	Wang, Tao,Yi, Jiangyan,Fu, Ruibo,Tao, Jianhua,&Wen, Zhengqi.(2022).CampNet: Context-Aware Mask Prediction for End-to-End Text-Based Speech Editing.IEEE-ACM TRANSACTIONS ON AUDIO SPEECH AND LANGUAGE PROCESSING,30,2241-2254.
MLA	Wang, Tao,et al."CampNet: Context-Aware Mask Prediction for End-to-End Text-Based Speech Editing".IEEE-ACM TRANSACTIONS ON AUDIO SPEECH AND LANGUAGE PROCESSING 30(2022):2241-2254.