Filters








1 Hit in 2.0 sec

PortaSpeech: Portable and High-Quality Generative Text-to-Speech [article]

Yi Ren, Jinglin Liu, Zhou Zhao
2022 arXiv   pre-print
Inspired by these observations, to generate diverse speech with natural details and rich prosody using a lightweight architecture, we propose PortaSpeech, a portable and high-quality generative text-to-speech  ...  Non-autoregressive text-to-speech (NAR-TTS) models such as FastSpeech 2 and Glow-TTS can synthesize high-quality speech from the given text in parallel.  ...  Conclusion In this paper, we proposed PortaSpeech, a portable and high-quality generative text-to-speech model.  ... 
arXiv:2109.15166v5 fatcat:3xm7izv4vfd6lbs5odoryje3qa