June-Woo Kim's repositories
adversarial_fine-tuning_using_generated_respiratory_sound
(NeurIPS 2023 Workshop on DGM4H) Official Implementation of "Adversarial Fine-tuning using Generated Respiratory Sound to Address Class Imbalance"
stethoscope-guided_supervised_contrastive_learning
(ICASSP 2024) Official Implementation of "Stethoscope-guided Supervised Contrastive Learning for Cross-domin Adaptation on Respiratory Sound Classification"
epd_for_vad
find end point with statistical voice activity detection model
improved_spoken_language_representation
Official code of Improved Spoken Language Representation for Intent Understanding in a Task-Oriented Dialogue System
military_audio_dataset
Official code implementation of "MAD: A Military Audio Dataset for Situational Awareness and Surveillance"
spec_augment
🔦 A Pytorch implementation of GoogleBrain's SpecAugment: A Simple Data Augmentation Method for Automatic Speech Recognition
al-folio
A beautiful, simple, clean, and responsive Jekyll theme for academics
ast
Code for the Interspeech 2021 paper "AST: Audio Spectrogram Transformer".
AudioMAE
This repo hosts the code and models of "Masked Autoencoders that Listen".
audiomentations
A Python library for audio data augmentation. Inspired by albumentations. Useful for machine learning.
GenSCL
Official Pytorch implementation of "Generalized Supervised Contrastive Learning Framework"
kenlm
KenLM: Faster and Smaller Language Model Queries
korean_speech_data_preprocessing
preprocessing of AIHub Korean speech dataset
Llama-2
All the projects related to Llama
lva
LG AI Intermediate Courses (Computer Vision)
nn_basic_2021
codes for neural network basic course
releasing-research-code
Tips for releasing research code in Machine Learning (with official NeurIPS 2020 recommendations)
s3prl_modified
s3prl modeification
self-supervised-speech-recognition
speech to text with self-supervised learning based on wav2vec 2.0 framework
ssast
Code for the AAAI 2022 paper "SSAST: Self-Supervised Audio Spectrogram Transformer".
SupContrast
PyTorch implementation of "Supervised Contrastive Learning" (and SimCLR incidentally)
vall-e
An unofficial PyTorch implementation of the audio LM VALL-E