Haibin Wu

A new framework for assessing foundation models in speech tasks.

Examining how codecs retain emotional tones in voice data.

This article discusses efficient training methods for speech models using self-supervised learning.

MCMamba model improves speech quality in noisy environments using spatial and spectral information.

This study evaluates low-latency methods for improving speech quality in noisy conditions.

A look at the Codec-SUPERB challenge results and codec performance metrics.

ESPnet-Codec enhances training and evaluation of neural codecs for audio and speech.

A new method improves efficiency in attention workloads for AI systems.

VERSA evaluates speech, audio, and music quality effectively.