2022/05/30 by Yinghao Aaron Li, Cong Han, Li, Yinghao Aaron +3 · 4 citations
Computer Science · Psychology · #Audio and Speech Processing (eess.AS) #Computation and Language (cs.CL) #FOS: Computer and information sciences #FOS: Electrical engineering #Machine Learning (cs.LG) #Phonetics and Phonology Research #Sound (cs.SD) #Speech Recognition and Synthesis #Speech and dialogue systems #electronic engineering #information engineering
paper · pdf · doi:10.48550/arxiv.2205.15439
openalex publication_date 2022/05/30 · openalex created_date 2023/02/14 · openalex updated_date 2026/07/28
Text-to-Speech (TTS) has recently seen great progress in synthesizing high-quality speech owing to the rapid development of parallel TTS systems, but producing speech with naturalistic prosodic variations, speaking styles and emotional tones remains challenging. Moreover, since duration and speech are generated separately, parallel TTS models still have problems finding the best monotonic alignments that are crucial for naturalistic speech synthesis. Here, we propose StyleTTS, a style-based generative model for parallel TTS that can synthesize diverse speech with natural prosody from a reference speech utterance. With novel Transferable Monotonic Aligner (TMA) and duration-invariant data augmentation schemes, our method significantly outperforms state-of-the-art models on both single and multi-speaker datasets in subjective tests of speech naturalness and speaker similarity. Through self-supervised learning of the speaking styles, our model can synthesize speech with the same prosodic and emotional tone as any given reference speech without the need for explicitly labeling these categories.