JustKowalski
Staff Algorithm Engineer at Alibaba. Grad from the School of Artificial Intelligence & Automation at HUST.
Pinned Repositories
asteroid
The PyTorch-based audio source separation toolkit for researchers
awesome-speech-enhancement
speech enhancement\speech seperation\sound source localization
ConferencesStastics
The stastics information of top conference realted to information area including AI, ML, CV, etc
DeepFilterNet
Noise supression using deep filtering
gitskills
learngit
MS-SNSD
The Microsoft Scalable Noisy Speech Dataset (MS-SNSD) is a noisy speech dataset that can scale to arbitrary sizes depending on the number of speakers, noise types, and Speech to Noise Ratio (SNR) levels desired.
NISQA
NISQA - Non-Intrusive Speech Quality and TTS Naturalness Assessment
Sound_event_detection
This code aims at weakly-labeled semi-supervised sound event detection. The code embraces two methods we proposed to solve this task: specialized decision surface (SDS) and disentangled feature (DF) for weakly-supervised learning and guided learning (GL) for semi-supervised learning. We're so glad if you're interested in using it for research purpose or DCASE participation.
sound_separation
JustKowalski's Repositories
JustKowalski/sound_separation
JustKowalski/ConferencesStastics
The stastics information of top conference realted to information area including AI, ML, CV, etc
JustKowalski/asteroid
The PyTorch-based audio source separation toolkit for researchers
JustKowalski/awesome-speech-enhancement
speech enhancement\speech seperation\sound source localization
JustKowalski/DeepFilterNet
Noise supression using deep filtering
JustKowalski/gitskills
JustKowalski/learngit
JustKowalski/MS-SNSD
The Microsoft Scalable Noisy Speech Dataset (MS-SNSD) is a noisy speech dataset that can scale to arbitrary sizes depending on the number of speakers, noise types, and Speech to Noise Ratio (SNR) levels desired.
JustKowalski/NISQA
NISQA - Non-Intrusive Speech Quality and TTS Naturalness Assessment
JustKowalski/Sound_event_detection
This code aims at weakly-labeled semi-supervised sound event detection. The code embraces two methods we proposed to solve this task: specialized decision surface (SDS) and disentangled feature (DF) for weakly-supervised learning and guided learning (GL) for semi-supervised learning. We're so glad if you're interested in using it for research purpose or DCASE participation.
JustKowalski/speech_recognition
end2end asr system with ctc + dynamic cnn transformer, well organized using custom template
JustKowalski/voice_datasets
🔊 A comprehensive list of open-source datasets for voice and sound computing (95+ datasets).
JustKowalski/wespeaker
Research and Production Oriented Speaker Recognition Toolkit