arxiv:2407.00837
Wangyou Zhang
wyz
AI & ML interests
Speech signal processing, robust speech recognition, self-supervised speech pre-training
Recent Activity
updated a model 3 days ago
wyz/librimix_tse_clean_2mix_training_td_speakerbeam_16k published a model 3 days ago
wyz/librimix_tse_clean_2mix_training_td_speakerbeam_16k upvoted an article 5 months ago
You could have designed state of the art positional encodingOrganizations
models 35
wyz/librimix_tse_clean_2mix_training_td_speakerbeam_16k
Audio-to-Audio • Updated • 11
wyz/vctk_bsrnn_xtiny_causal
Audio-to-Audio • Updated • 3
wyz/vctk_bsrnn_tiny_causal
Audio-to-Audio • Updated
wyz/vctk_bsrnn_small_causal
Audio-to-Audio • Updated
wyz/vctk_bsrnn_medium_causal
Audio-to-Audio • Updated • 2
wyz/vctk_bsrnn_large_causal
Audio-to-Audio • Updated • 2
wyz/vctk_bsrnn_large_double_causal
Audio-to-Audio • Updated • 5
wyz/vctk_bsrnn_xtiny_noncausal
Audio-to-Audio • Updated
wyz/vctk_bsrnn_tiny_noncausal
Audio-to-Audio • Updated
wyz/vctk_bsrnn_small_noncausal
Audio-to-Audio • Updated • 4
datasets 0
None public yet