Comparative Analysis of Fast and High-Fidelity Neural Vocoders for Low-Latency Streaming Synthesis in Resource-Constrained Environments

Sep 1, 2025·

Reo Yoneyama

Masaya Kawamura

Masaya Kawamura

,

Ryo Terashima, Ryuichi Yamamoto, Tomoki Toda

· 0 min read

PDF arXiv

Type

Conference paper

Publication

In Proceedings of Interspeech

Last updated on Sep 1, 2025

Interspeech tts speech

Masaya Kawamura

Authors

Masaya Kawamura

← BitTTS: Highly Compact Text-to-Speech Using 1.58-bit Quantization and Weight Indexing Sep 1, 2025

SLASH: Self-Supervised Speech Pitch Estimation Leveraging DSP-derived Absolute Pitch Sep 1, 2025 →