YUCHEN005

STAR-Adapt

Code for paper "Self-Taught Recognizer: Toward Unsupervised Adaptation for Speech Foundation Models"

GenTranslate

Code for paper "GenTranslate: Large Language Models are Generative Multilingual Speech and Machine Translators"

RobustGER

Code for paper "Large Language Models are Efficient Learners of Noise-Robust Speech Recognition"

NASE

Code for paper "Noise-aware Speech Enhancement using Diffusion Probabilistic Model"

DPSL-ASR

Code for paper "Dual-Path Style Learning for End-to-End Noise-Robust Speech Recognition"

Unified-Enhance-Separation

Code for paper "Unifying Speech Enhancement and Separation with Gradient Modulation for End-to-End Noise-Robust Speech Separation"

GILA

Code for paper "Cross-Modal Global Interaction and Local Alignment for Audio-Visual Speech Recognition"

MIR-GAN

Code for paper "MIR-GAN: Refining Frame-Level Modality-Invariant Representations with Adversarial Network for Audio-Visual Speech Recognition"

Gradient-Remedy

Code for paper "Gradient Remedy for Multi-Task Learning in End-to-End Noise-Robust Speech Recognition"

UniVPM

Code for paper "Hearing Lips in Noise: Universal Viseme-Phoneme Mapping and Transfer for Robust Audio-Visual Speech Recognition"

RATS-Channel-A-Speech-Data

This is a public repository for RATS Channel-A Speech Data, which is a chargeable noisy speech dataset under LDC. Here we release its Log-Mel Fbank features and several raw wavform listening samples.

UNA-GAN

Code for paper "Unsupervised Noise adaptation using Data Simulation"

UNA-GAN-Demo

Hypo2Trans

Single-blind supplementary materials for NeurIPS 2023 submission

RIO-TTS-demos

UNO-TTS-demos

yuchen005.github.io

AcadHomepage: A Modern and Responsive Academic Personal Homepage