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

Fuente: arXiv
Enregistré dans:
Détails bibliographiques
Auteurs principaux: Yoneyama, Reo, Kawamura, Masaya, Terashima, Ryo, Yamamoto, Ryuichi, Toda, Tomoki
Format: Preprint
Publié: 2025
Sujets:
Accès en ligne:
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866915324122628096
author Yoneyama, Reo
Kawamura, Masaya
Terashima, Ryo
Yamamoto, Ryuichi
Toda, Tomoki
author_facet Yoneyama, Reo
Kawamura, Masaya
Terashima, Ryo
Yamamoto, Ryuichi
Toda, Tomoki
contents In real-time speech synthesis, neural vocoders often require low-latency synthesis through causal processing and streaming. However, streaming introduces inefficiencies absent in batch synthesis, such as limited parallelism, inter-frame dependency management, and parameter loading overhead. This paper proposes multi-stream Wavehax (MS-Wavehax), an efficient neural vocoder for low-latency streaming, by extending the aliasing-free neural vocoder Wavehax with multi-stream decomposition. We analyze the latency-throughput trade-off in a CPU-only environment and identify key bottlenecks in streaming neural vocoders. Our findings provide practical insights for optimizing chunk sizes and designing vocoders tailored to specific application demands and hardware constraints. Furthermore, our subjective evaluations show that MS-Wavehax delivers high speech quality under causal and non-causal conditions while being remarkably compact and easily deployable in resource-constrained environments.
format Preprint
id arxiv_https___arxiv_org_abs_2506_03554
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Comparative Analysis of Fast and High-Fidelity Neural Vocoders for Low-Latency Streaming Synthesis in Resource-Constrained Environments
Yoneyama, Reo
Kawamura, Masaya
Terashima, Ryo
Yamamoto, Ryuichi
Toda, Tomoki
Sound
Audio and Speech Processing
In real-time speech synthesis, neural vocoders often require low-latency synthesis through causal processing and streaming. However, streaming introduces inefficiencies absent in batch synthesis, such as limited parallelism, inter-frame dependency management, and parameter loading overhead. This paper proposes multi-stream Wavehax (MS-Wavehax), an efficient neural vocoder for low-latency streaming, by extending the aliasing-free neural vocoder Wavehax with multi-stream decomposition. We analyze the latency-throughput trade-off in a CPU-only environment and identify key bottlenecks in streaming neural vocoders. Our findings provide practical insights for optimizing chunk sizes and designing vocoders tailored to specific application demands and hardware constraints. Furthermore, our subjective evaluations show that MS-Wavehax delivers high speech quality under causal and non-causal conditions while being remarkably compact and easily deployable in resource-constrained environments.
title Comparative Analysis of Fast and High-Fidelity Neural Vocoders for Low-Latency Streaming Synthesis in Resource-Constrained Environments
topic Sound
Audio and Speech Processing
url https://arxiv.org/abs/2506.03554