kjw11's repositories
tf-kaldi-speaker
Neural speaker recognition/verification system based on Kaldi and Tensorflow
CSEnet-ASR
Cross-Speaker Encoding Network for Multi-talker Speech Recognition
MAML-Speaker
MAML-based domain generalization method for multi-condition speaker recognition.
Robust-MAML
Robust MAML for domain generalization in speaker embedding.
Language:Perl000
AudioSamplesPage
this is a page for synthesized mandarin audio samples
Language:HTML000
BeamformIt_njob
Njob script for BeamformIt.
Language:Shell000
Language:Shell000
Language:JavaScript000
masf
Domain Generalization via Model-Agnostic Learning of Semantic Features
Apache-2.0000
RIDE-LongTailRecognition
[ICLR 2021 Spotlight] Pytorch implementation for "Long-tailed Recognition by Routing Diverse Distribution-Aware Experts."
MIT000
Language:Python000