3 papers
cs.CL2026
Speaker-Disentangled Chunk-Wise Regression for Syllabic Tokenization
Ryota Komatsu, Kota Kawakita, Takuma Okamoto +1
Unsupervised syllabic tokenization aims to learn discrete syllabic tokens that capture latent linguistic content-related structure from raw speech. Recent syllabic tokenization met…
eess.AS2026
WaveNeXt 2: ConvNeXt-Based Fast Neural Vocoders With Residual Denoising and Sub-Modeling for GAN and Diffusion Models
Wangzixi Zhou, Takuma Okamoto, Yamato Ohtani +2
Most neural vocoders are limited to one type: either GAN or diffusion-based. While state-of-the-art models like Vocos and WaveNeXt use powerful ConvNeXt-based generators, they have…
eess.AS2025
Layer-wise Analysis for Quality of Multilingual Synthesized Speech
Erica Cooper, Takuma Okamoto, Yamato Ohtani +2
While supervised quality predictors for synthesized speech have demonstrated strong correlations with human ratings, their requirement for in-domain labeled training data hinders t…