Name: Ho-Gun, Yu
Type: User
Company: Sogang IIP Lab
Bio: 22.1~22.7 : Carnegie Mellon
23.1~ : HMC Rototics Lab
---------------
Interest subject : Multichannel Speech for SE, SS, SSL, KWS
Location: Pittsburgh, Pennsylvania
Ho-Gun, Yu's Projects
Acoustic Echo Cancellation
A collection of resources and papers on Diffusion Models
This repository contains best profile readme's for your reference.
A curated list of awesome open source libraries to deploy, monitor, version and scale your machine learning
A curated list of awesome READMEs
speech enhancement\speech seperation\sound source localization
simple delaysum, MVDR and CGMM-MVDR
Fine-tuning StyleGAN2 for Cartoon Face Generation
Text-to-video generation.
RES via complex-valued DNN
The Cone of Silence:
DeepStream SDK Python bindings and sample applications
Diarization scoring tools.
Dual-signal Transformation LSTM Network, PyTorch,NCNN
This is the official implementation of our neural-network-based fast diffuse room impulse response generator (FAST-RIR) for generating room impulse responses (RIRs) for a given acoustic environment.
Unofficial Pytorch Convolutive Prediction for Monaural Speech Dereverberation and Noisy-Reverberant Speaker Separation(FCP) https://ieeexplore.ieee.org/abstract/document/9622185
Google Research
Python library for Room Impulse Response (RIR) simulation with GPU acceleration
As easy as /aitch-tee-tee-pie/ 🥧 Modern, user-friendly command-line HTTP client for the API era. JSON support, colors, sessions, downloads, plugins & more. https://twitter.com/httpie
TensorFlow and PyTorch implementation of "Meta-Transfer Learning for Few-Shot Learning" (CVPR2019)
Unofficial Multi-microphone complex spectral mapping for utterance-wise and continuous speech separation(MISO-BF-MISO)
In this project, I implemented, evaluated, operated, monitored, and evolved a recommendation service for a scenario of a movie streaming service.
An unofficial implementation of the Personal VAD speaker-conditioned voice activity detection method. Bachelor's thesis project.
On-device wake word detection powered by deep learning
simple and efficient python implemention of a series of adaptive filters. including time domain adaptive filters(lms、nlms、rls、ap、kalman)、nonlinear adaptive filters(volterra filter、functional link adaptive filters)、frequency domain adaptive filters(frequency domain adaptive filter、frequency domain kalman filter) for acoustic echo cancellation.
The easiest way to use deep metric learning in your application. Modular, flexible, and extensible. Written in PyTorch.