DanielLin94144

StyleTalk

Official release of StyleTalk dataset.

DUAL-textless-SQA

Textless (ASR-transcript free) Spoken Question Answering. The official release of NMSQA dataset and the implementation of "DUAL: Textless Spoken Question Answering with Speech Discrete Unit Adaptive Learning" paper.

Test-time-adaptation-ASR-SUTA

Test-time adaptation for speech recognition model by single utterance. The official implementation of "Listen, Adapt, Better WER: Source-free Single-utterance Test-time Adaptation for Automatic Speech Recognition" paper.

E2E-ASR-Pytorch

End-to-End-jointCTC-Attention-ASR

unsupervised_ASR_challenge

Facebook AI Research Sequence-to-Sequence Toolkit written in Python.

Algorithm

NTHU EE3980

DanielLin94144.github.io

Github Pages template for academic personal websites, forked from mmistakes/minimal-mistakes

FixMatch-pytorch

Unofficial PyTorch implementation of "FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidence"

Protect-Your-Voice

Official implementation of Meta-StyleSpeech and StyleSpeech

AudioMAE

This repo hosts the code and models of "Masked Autoencoders that Listen".

CLUENER2020

CLUENER2020 中文细粒度命名实体识别 Fine Grained Named Entity Recognition

CPC_audio

An implementation of the Contrast Predictive Coding (CPC) method to train audio features in an unsupervised fashion.

DM2020-Lab1-Homework1

DM2020-Lab2-Homework

DM2020-Lab2-Master

Emphasized-Talk

Official release of Emphasized-Talk

FastSpeech2

An implementation of Microsoft's "FastSpeech 2: Fast and High-Quality End-to-End Text to Speech"

fixmatch

A simple method to perform semi-supervised learning with limited data.

GlossBERT

GlossBERT: BERT for Word Sense Disambiguation with Gloss Knowledge (EMNLP 2019)

hubert-cluster-code

Extract clustering feature from hubert

Linear_Algebra_2023fall_Hw3

Meta-TTS

Official repository of https://arxiv.org/abs/2111.04040v1

ML-attack-dataset

MLSS-2021-Taipei-Collaborative-Notes

mulit

SpeechMix

Explore different way to mix speech model(wav2vec2, hubert) and nlp model(BART,T5,GPT) together

tango

Codes and Model of the paper "Text-to-Audio Generation using Instruction Tuned LLM and Latent Diffusion Model"

tent

ICLR21 Tent: Fully Test-Time Adaptation by Entropy Minimization

VISinger2

VISinger 2: High-Fidelity End-to-End Singing Voice Synthesis Enhanced by Digital Signal Processing Synthesizer