YUCHEN005/Gradient-Remedy YUCHEN005/Gradient-Remedy

  • Stars
    star
    13
  • Rank 1,504,369 (Top 30 %)
  • Language
    Python
  • License
    Apache License 2.0
  • Created about 2 years ago
  • Updated over 1 year ago
Twitter logo Share LinkedIn logo Share Facebook logo Share
YUCHEN005/Gradient-Remedy
github

YUCHEN005

Reviews

There are no reviews yet. Be the first to send feedback to the community and the maintainers!

Repository Details

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

More Repositories

1

STAR-Adapt

Code for paper "Self-Taught Recognizer: Toward Unsupervised Adaptation for Speech Foundation Models"
Python
241
star
2

GenTranslate

Code for paper "GenTranslate: Large Language Models are Generative Multilingual Speech and Machine Translators"
Python
189
star
3

RobustGER

Code for paper "Large Language Models are Efficient Learners of Noise-Robust Speech Recognition"
Python
113
star
4

NASE

Code for paper "Noise-aware Speech Enhancement using Diffusion Probabilistic Model"
Python
80
star
5

DPSL-ASR

Code for paper "Dual-Path Style Learning for End-to-End Noise-Robust Speech Recognition"
Python
35
star
6

Unified-Enhance-Separation

Code for paper "Unifying Speech Enhancement and Separation with Gradient Modulation for End-to-End Noise-Robust Speech Separation"
Python
34
star
7

GILA

Code for paper "Cross-Modal Global Interaction and Local Alignment for Audio-Visual Speech Recognition"
Python
17
star
8

MIR-GAN

Code for paper "MIR-GAN: Refining Frame-Level Modality-Invariant Representations with Adversarial Network for Audio-Visual Speech Recognition"
Python
14
star
9

UniVPM

Code for paper "Hearing Lips in Noise: Universal Viseme-Phoneme Mapping and Transfer for Robust Audio-Visual Speech Recognition"
Python
12
star
10

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.
11
star
11

UNA-GAN

Code for paper "Unsupervised Noise adaptation using Data Simulation"
Python
6
star
12

UNA-GAN-Demo

HTML
2
star