M2-CTTS: End-to-End Multi-scale Multi-modal Conversational Text-to-Speech Synthesis

Autor:	Xue, Jinlong, Deng, Yayue, Wang, Fengping, Li, Ya, Gao, Yingming, Tao, Jianhua, Sun, Jianqing, Liang, Jiaen
Rok vydání:	2023
Předmět:	Computer Science - Sound Computer Science - Computation and Language Electrical Engineering and Systems Science - Audio and Speech Processing
Druh dokumentu:	Working Paper
Popis:	Conversational text-to-speech (TTS) aims to synthesize speech with proper prosody of reply based on the historical conversation. However, it is still a challenge to comprehensively model the conversation, and a majority of conversational TTS systems only focus on extracting global information and omit local prosody features, which contain important fine-grained information like keywords and emphasis. Moreover, it is insufficient to only consider the textual features, and acoustic features also contain various prosody information. Hence, we propose M2-CTTS, an end-to-end multi-scale multi-modal conversational text-to-speech system, aiming to comprehensively utilize historical conversation and enhance prosodic expression. More specifically, we design a textual context module and an acoustic context module with both coarse-grained and fine-grained modeling. Experimental results demonstrate that our model mixed with fine-grained context information and additionally considering acoustic features achieves better prosody performance and naturalness in CMOS tests. Comment: 5 pages, 1 figures, 2 tables. Accepted by ICASSP 2023
Databáze:	arXiv
Externí odkaz:	http://arxiv.org/abs/2305.02269 Zobrazit plný text záznamu View this record from Arxiv