@inproceedings{db3fc6a9a0e04ba59b398a0cdbaf2576,
title = "Reinforce-Aligner: Reinforcement alignment search for robust end-to-end text-to-speech",
abstract = "Text-to-speech (TTS) synthesis is the process of producing synthesized speech from text or phoneme input. Traditional TTS models contain multiple processing steps and require external aligners, which provide attention alignments of phoneme-to-frame sequences. As the complexity increases and efficiency decreases with every additional step, there is expanding demand in modern synthesis pipelines for end-to-end TTS with efficient internal aligners. In this work, we propose an end-to-end text-to-waveform network with a novel reinforcement learning based duration search method. Our proposed generator is feed-forward and the aligner trains the agent to make optimal duration predictions by receiving active feedback from actions taken to maximize cumulative reward. We demonstrate accurate alignments of phoneme-to-frame sequence generated from trained agents enhance fidelity and naturalness of synthesized audio. Experimental results also show the superiority of our proposed model compared to other state-of-the-art TTS models with internal and external aligners.",
keywords = "Reinforcement learning, Text to speech",
author = "Hyunseung Chung and Lee, {Sang Hoon} and Lee, {Seong Whan}",
note = "Funding Information: This work was supported by Institute of Information & communications Technology Planning & Evaluation (IITP) grant funded by the Korea government (MSIT) (No. 2019-0-00079, Department of Artificial Intelligence, Korea University), and the Netmarble AI Center. Publisher Copyright: {\textcopyright} 2021 ISCA; 22nd Annual Conference of the International Speech Communication Association, INTERSPEECH 2021 ; Conference date: 30-08-2021 Through 03-09-2021",
year = "2021",
doi = "10.21437/Interspeech.2021-831",
language = "English",
series = "Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH",
publisher = "International Speech Communication Association",
pages = "3556--3560",
booktitle = "22nd Annual Conference of the International Speech Communication Association, INTERSPEECH 2021",
}