Sidon: Fast and Robust Open-Source Multilingual Speech Restoration for Large-scale Dataset Cleansing

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Nakata, Wataru, Saito, Yuki, Ueda, Yota, Saruwatari, Hiroshi
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866918304340246528
author Nakata, Wataru
Saito, Yuki
Ueda, Yota
Saruwatari, Hiroshi
author_facet Nakata, Wataru
Saito, Yuki
Ueda, Yota
Saruwatari, Hiroshi
contents Large-scale text-to-speech (TTS) systems are limited by the scarcity of clean, multilingual recordings. We introduce Sidon, a fast, open-source speech restoration model that converts noisy in-the-wild speech into studio-quality speech and scales to dozens of languages. Sidon consists of two models: w2v-BERT 2.0 finetuned feature predictor to cleanse features from noisy speech and vocoder trained to synthesize restored speech from the cleansed features. Sidon achieves restoration performance comparable to Miipher: Google's internal speech restoration model with the aim of dataset cleansing for speech synthesis. Sidon is also computationally efficient, running up to 500 times faster than real time on a single GPU. We further show that training a TTS model using a Sidon-cleansed automatic speech recognition corpus improves the quality of synthetic speech in a zero-shot setting. Code and model are released to facilitate reproducible dataset cleansing for the research community.
format Preprint
id arxiv_https___arxiv_org_abs_2509_17052
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Sidon: Fast and Robust Open-Source Multilingual Speech Restoration for Large-scale Dataset Cleansing
Nakata, Wataru
Saito, Yuki
Ueda, Yota
Saruwatari, Hiroshi
Sound
Audio and Speech Processing
Large-scale text-to-speech (TTS) systems are limited by the scarcity of clean, multilingual recordings. We introduce Sidon, a fast, open-source speech restoration model that converts noisy in-the-wild speech into studio-quality speech and scales to dozens of languages. Sidon consists of two models: w2v-BERT 2.0 finetuned feature predictor to cleanse features from noisy speech and vocoder trained to synthesize restored speech from the cleansed features. Sidon achieves restoration performance comparable to Miipher: Google's internal speech restoration model with the aim of dataset cleansing for speech synthesis. Sidon is also computationally efficient, running up to 500 times faster than real time on a single GPU. We further show that training a TTS model using a Sidon-cleansed automatic speech recognition corpus improves the quality of synthetic speech in a zero-shot setting. Code and model are released to facilitate reproducible dataset cleansing for the research community.
title Sidon: Fast and Robust Open-Source Multilingual Speech Restoration for Large-scale Dataset Cleansing
topic Sound
Audio and Speech Processing
url https://arxiv.org/abs/2509.17052