Pinned Repositories
aspire-sad
AudioSamplesPage
this is a page for synthesized mandarin audio samples
BeamformIt_njob
Njob script for BeamformIt.
CSEnet-ASR
Cross-Speaker Encoding Network for Multi-talker Speech Recognition
Feature-segmentation
kaldi
Kaldi with CN-Celeb recipes
kjw11.github.io
pp
MAML-Speaker
MAML-based domain generalization method for multi-condition speaker recognition.
Robust-MAML
Robust MAML for domain generalization in speaker embedding.
tf-kaldi-speaker
Neural speaker recognition/verification system based on Kaldi and Tensorflow
kjw11's Repositories
kjw11/tf-kaldi-speaker
Neural speaker recognition/verification system based on Kaldi and Tensorflow
kjw11/CSEnet-ASR
Cross-Speaker Encoding Network for Multi-talker Speech Recognition
kjw11/MAML-Speaker
MAML-based domain generalization method for multi-condition speaker recognition.
kjw11/kaldi
Kaldi with CN-Celeb recipes
kjw11/Robust-MAML
Robust MAML for domain generalization in speaker embedding.
kjw11/aspire-sad
kjw11/AudioSamplesPage
this is a page for synthesized mandarin audio samples
kjw11/BeamformIt_njob
Njob script for BeamformIt.
kjw11/Feature-segmentation
kjw11/kjw11.github.io
pp
kjw11/masf
Domain Generalization via Model-Agnostic Learning of Semantic Features
kjw11/RIDE-LongTailRecognition
[ICLR 2021 Spotlight] Pytorch implementation for "Long-tailed Recognition by Routing Diverse Distribution-Aware Experts."
kjw11/v2wPipelineDemo