← Search

Wataru Nakata

2 accepted papers

2026

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

ICASSP 2026poster

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:…

Cited by 0SourcePDFScholar
2025

Causal Speech Enhancement with Predicting Semantics based on Quantized Self-supervised Learning Features

ICASSP 2025accepted

Real-time speech enhancement (SE) is essential to online speech communication. Causal SE models use only the previous context while predicting future information, such as phoneme continuation, may help performing causal SE. The phonetic information is often represented by quantizing latent features…

Cited by 0SourceScholar