← Search

Hien Ohnaka

2 accepted papers

2026

WAVE-TRAINER-FIT: NEURAL VOCODER WITH TRAINABLE PRIOR AND FIXED-POINT ITERATION TOWARDS HIGH-QUALITY SPEECH GENERATION FROM SSL FEATURES

ICASSP 2026poster

We propose WaveTrainerFit, a neural vocoder that performs high-quality waveform generation from data-driven features such as SSL features. WaveTrainerFit builds upon the WaveFit vocoder, which integrates diffusion model and generative adversarial network. Furthermore, the proposed method incorporate…

Cited by 0Source ↗PDF ↗Scholar ↗
2023

Visual Onoma-to-Wave: Environmental Sound Synthesis from Visual Onomatopoeias and Sound-Source Images

ICASSP 2023accepted

We propose a method for synthesizing environmental sounds from visually represented onomatopoeias and sound sources. An onomatopoeia is a word that imitates a sound structure, i.e., the text representation of sound. From this perspective, onoma-to-wave has been proposed to synthesize environmental s…

Cited by 0Source ↗Scholar ↗