Name: Dongkeon Park
Type: User
Company: GIST (Gwangju Institute of Science and Technology)
Bio: Currently pursuing my Ph.D., I am deeply intrigued by the field of speaker diarization and committed to making meaningful contributions to it
Location: Gwangju, Republic of Korea
Blog: https://velog.io/@dongkeon
Dongkeon Park's Projects
Problem Generator for Math Word Prediction
Summary of DeepLearning (Korean and English are included)
Some comprehensive papers about speaker diarization
바벨스피치 (캐글뽀개기X바벨피쉬 콜라보 스터디 자료보관용)
UrbanSound classification using Convolutional Recurrent Networks in PyTorch
NLP blog
This repository contains a set of codes to run (i.e., train, perform inference with, evaluate) a diarization method called EEND-vector-clustering.
Implementation of "End-to-End Speaker Diarization as Post-Processing"
Fast Incremental Support Vector Data Description implemented in Python
3rd Grand Challenge track 3 DB developed by GIST
Deep learning based autism spectral disorder detection from children voice
LoCoNet: Long-Short Context Network for Active Speaker Detection (2023 CVPR)
Models and examples built with TensorFlow
Deep speaker embeddings in PyTorch, including x-vectors. Code used in this work: https://arxiv.org/abs/2007.16196
RASTA-PLP and MFCC tool based rasta-mat
Self-Supervised Speech Pre-training and Representation Learning Toolkit.
Learning Long-Term Spatial-Temporal Graphs for Active Speaker Detection (ECCV 2022)
Code for the AAAI 2022 paper "SSAST: Self-Supervised Audio Spectrogram Transformer".
ACM MM 2021: 'Is Someone Speaking? Exploring Long-term Temporal Features for Audio-visual Active Speaker Detection'
theorydb's blog
🤗 Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX.
INTERSPEECH2023: Target Active Speaker Detection with Audio-visual Cues
In defence of metric learning for speaker recognition
Audio event detection model based on YOLOX