Bunched LPCNet2: Efficient Neural Vocoders Covering Devices from Cloud to Edge

Autor:	Park, Sangjun, Choo, Kihyun, Lee, Joohyung, Porov, Anton V., Osipov, Konstantin, Sung, June Sig
Rok vydání:	2022
Předmět:	Electrical Engineering and Systems Science - Audio and Speech Processing Computer Science - Machine Learning Computer Science - Sound
Druh dokumentu:	Working Paper
Popis:	Text-to-Speech (TTS) services that run on edge devices have many advantages compared to cloud TTS, e.g., latency and privacy issues. However, neural vocoders with a low complexity and small model footprint inevitably generate annoying sounds. This study proposes a Bunched LPCNet2, an improved LPCNet architecture that provides highly efficient performance in high-quality for cloud servers and in a low-complexity for low-resource edge devices. Single logistic distribution achieves computational efficiency, and insightful tricks reduce the model footprint while maintaining speech quality. A DualRate architecture, which generates a lower sampling rate from a prosody model, is also proposed to reduce maintenance costs. The experiments demonstrate that Bunched LPCNet2 generates satisfactory speech quality with a model footprint of 1.1MB while operating faster than real-time on a RPi 3B. Our audio samples are available at https://srtts.github.io/bunchedLPCNet2. Comment: Interspeech 2022
Databáze:	arXiv
Externí odkaz:	http://arxiv.org/abs/2203.14416 Zobrazit plný text záznamu View this record from Arxiv