{"ID":2868140,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2509.17052","arxiv_id":"2509.17052","title":"Sidon: Fast and Robust Open-Source Multilingual Speech Restoration for Large-scale Dataset Cleansing","abstract":"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.","short_abstract":"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 finetun...","url_abs":"https://arxiv.org/abs/2509.17052","url_pdf":"https://arxiv.org/pdf/2509.17052v3","authors":"[\"Wataru Nakata\",\"Yuki Saito\",\"Yota Ueda\",\"Hiroshi Saruwatari\"]","published":"2025-09-21T12:17:12Z","proceeding":"cs.SD","tasks":"[\"cs.SD\",\"eess.AS\"]","methods":"[]","has_code":false}