espnet/chenda-li-wsj0_2mix_enh_train_enh_rnn_tf_raw_valid.si_snr.ave
Audio-to-Audio
•
Updated
•
6
AI & ML interests
voice-conversion speech-separation speech-enhancement speech-translation speech-synthesis speech-recognition spoken-language-understanding
Recent Activity
espnet/anogkongda-librimix_enh_train_raw_valid.si_snr.ave
Audio-to-Audio
•
Updated
•
3
espnet/Emiru_Tsunoo_aishell_asr_train_asr_streaming_transformer_raw_zh_char_sp_valid.acc.ave
Automatic Speech Recognition
•
Updated
espnet/kamo-naoyuki_librispeech_asr_train_asr_conformer6_n_fft512_hop_length2-truncated-a63357
Automatic Speech Recognition
•
Updated
•
1
espnet/Shinji_Watanabe_spgispeech_asr_train_asr_conformer6_n_fft512_hop_lengt-truncated-f1ac86
Automatic Speech Recognition
•
Updated
•
1
•
1
espnet/Shinji_Watanabe_spgispeech_asr_train_asr_conformer6_n_fft512_hop_lengt-truncated-a013d0
Automatic Speech Recognition
•
Updated
espnet/Chenda_Li_wsj0_2mix_enh_train_enh_rnn_tf_raw_valid.si_snr.ave
Audio-to-Audio
•
Updated
•
2
espnet/Chenda_Li_wsj0_2mix_enh_train_enh_conv_tasnet_raw_valid.si_snr.ave
Audio-to-Audio
•
Updated
•
3
espnet/anogkongda_librimix_enh_train_raw_valid.si_snr.ave
Audio-to-Audio
•
Updated
espnet/ftshijt_mls_asr_transformer_valid.acc.best
Automatic Speech Recognition
•
Updated
espnet/Shinji_Watanabe_laborotv_asr_train_asr_conformer2_latest33_raw_char_sp_valid.acc.ave
Automatic Speech Recognition
•
Updated
•
5
•
1
espnet/kamo-naoyuki_librispeech_asr_train_asr_conformer5_raw_bpe5000_frontend-truncated-b76af5
Automatic Speech Recognition
•
Updated
espnet/kamo-naoyuki_librispeech_asr_train_asr_conformer5_raw_bpe5000_frontend-truncated-55c091
Automatic Speech Recognition
•
Updated
•
2
espnet/kamo-naoyuki_librispeech_asr_train_asr_conformer5_raw_bpe5000_schedule-truncated-c8e5f9
Automatic Speech Recognition
•
Updated
espnet/kan-bayashi_jsut_conformer_fastspeech2_accent_with_pause
Text-to-Speech
•
Updated
•
1
espnet/kan-bayashi_jsut_fastspeech2_accent_with_pause
Text-to-Speech
•
Updated
•
1
espnet/kan-bayashi_jsut_transformer_accent_with_pause
Text-to-Speech
•
Updated
•
2
espnet/kan-bayashi_jsut_tacotron2_accent_with_pause
Text-to-Speech
•
Updated
espnet/kan-bayashi_jsut_tts_train_conformer_fastspeech2_transformer_teacher_r-truncated-74c1b4
Text-to-Speech
•
Updated
espnet/kan-bayashi_jsut_tts_train_fastspeech2_transformer_teacher_raw_phn_jac-truncated-60fc24
Text-to-Speech
•
Updated
•
3
espnet/kan-bayashi_jsut_tts_train_conformer_fastspeech2_tacotron2_teacher_raw-truncated-a7f080
Text-to-Speech
•
Updated
•
1
espnet/kan-bayashi_jsut_tts_train_fastspeech2_tacotron2_teacher_raw_phn_jacon-truncated-e5d906
Text-to-Speech
•
Updated
•
1
espnet/kan-bayashi_jsut_tts_train_transformer_raw_phn_jaconv_pyopenjtalk_acce-truncated-be0f66
Text-to-Speech
•
Updated
espnet/kan-bayashi_jsut_tts_train_tacotron2_raw_phn_jaconv_pyopenjtalk_accent_with_pause_train.loss.ave
Text-to-Speech
•
Updated
espnet/kamo-naoyuki_reverb_asr_train_asr_transformer2_raw_en_char_rir_scpdata-truncated-0e9753
Automatic Speech Recognition
•
Updated
espnet/kamo-naoyuki_hkust_asr_train_asr_transformer2_raw_zh_char_batch_bins20-truncated-934e17
Automatic Speech Recognition
•
Updated
•
1
espnet/kan-bayashi_libritts_gst_xvector_conformer_fastspeech2
Text-to-Speech
•
Updated
espnet/kan-bayashi_libritts_xvector_conformer_fastspeech2
Text-to-Speech
•
Updated
espnet/kan-bayashi_libritts_gst_xvector_trasnformer
Text-to-Speech
•
Updated
espnet/kan-bayashi_libritts_xvector_trasnformer
Text-to-Speech
•
Updated