Laugh Now Cry Later: Controlling Time-Varying Emotional States of Flow-Matching-Based Zero-Shot Text-to-Speech

Autor:	Wu, Haibin, Wang, Xiaofei, Eskimez, Sefik Emre, Thakker, Manthan, Tompkins, Daniel, Tsai, Chung-Hsien, Li, Canrun, Xiao, Zhen, Zhao, Sheng, Li, Jinyu, Kanda, Naoyuki
Rok vydání:	2024
Předmět:	Electrical Engineering and Systems Science - Audio and Speech Processing Computer Science - Artificial Intelligence Electrical Engineering and Systems Science - Signal Processing
Druh dokumentu:	Working Paper
Popis:	People change their tones of voice, often accompanied by nonverbal vocalizations (NVs) such as laughter and cries, to convey rich emotions. However, most text-to-speech (TTS) systems lack the capability to generate speech with rich emotions, including NVs. This paper introduces EmoCtrl-TTS, an emotion-controllable zero-shot TTS that can generate highly emotional speech with NVs for any speaker. EmoCtrl-TTS leverages arousal and valence values, as well as laughter embeddings, to condition the flow-matching-based zero-shot TTS. To achieve high-quality emotional speech generation, EmoCtrl-TTS is trained using more than 27,000 hours of expressive data curated based on pseudo-labeling. Comprehensive evaluations demonstrate that EmoCtrl-TTS excels in mimicking the emotions of audio prompts in speech-to-speech translation scenarios. We also show that EmoCtrl-TTS can capture emotion changes, express strong emotions, and generate various NVs in zero-shot TTS. See https://aka.ms/emoctrl-tts for demo samples. Comment: Accepted by SLT2024. See https://aka.ms/emoctrl-tts for demo samples
Databáze:	arXiv
Externí odkaz:	http://arxiv.org/abs/2407.12229 Zobrazit plný text záznamu View this record from Arxiv