YODAS v3: A 1 Million Hour Dataset for the Next Generation of Open Voice AI Research
• 24
AI & ML interests
voice-conversion speech-separation speech-enhancement speech-translation speech-synthesis speech-recognition spoken-language-understanding
Recent Activity
View all activity
Articles
espnet/kan-bayashi_jsut_tts_train_fastspeech2_tacotron2_teacher_raw_phn_jacon-truncated-f45dcb
Text-to-Speech • Updated • 9
espnet/kan-bayashi_jsut_tts_train_fastspeech2_raw_phn_jaconv_pyopenjtalk_train.loss.ave
Text-to-Speech • Updated • 10
espnet/kan-bayashi_jsut_tts_train_conformer_fastspeech2_transformer_teacher_r-truncated-74c1b4
Text-to-Speech • Updated • 9
espnet/kan-bayashi_jsut_tts_train_conformer_fastspeech2_transformer_teacher_r-truncated-f43d8f
Text-to-Speech • Updated • 8
espnet/kan-bayashi_jsut_tts_train_conformer_fastspeech2_transformer_teacher_r-truncated-35ef5a
Text-to-Speech • Updated • 12
espnet/kan-bayashi_jsut_tts_train_conformer_fastspeech2_tacotron2_teacher_raw-truncated-569e81
Text-to-Speech • Updated • 12
espnet/kan-bayashi_jsut_tts_train_conformer_fastspeech2_tacotron2_teacher_raw-truncated-a7f080
Text-to-Speech • Updated • 11
espnet/kan-bayashi_jsut_tts_train_conformer_fastspeech2_tacotron2_teacher_raw-truncated-15ef5f
Text-to-Speech • Updated • 9
espnet/kan-bayashi_jsut_tts_train_conformer_fastspeech2_raw_phn_jaconv_pyopenjtalk_train.loss.ave
Text-to-Speech • Updated • 6
espnet/kan-bayashi_jsut_transformer_prosody
Text-to-Speech • Updated • 10
espnet/kan-bayashi_jsut_transformer_accent_with_pause
Text-to-Speech • Updated • 8
espnet/kan-bayashi_jsut_transformer_accent
Text-to-Speech • Updated • 8
espnet/kan-bayashi_jsut_transformer
Text-to-Speech • Updated • 10
espnet/kan-bayashi_jsut_tacotron2_prosody
Text-to-Speech • Updated • 11
espnet/kan-bayashi_jsut_tacotron2_accent_with_pause
Text-to-Speech • Updated • 6
espnet/kan-bayashi_jsut_tacotron2_accent
Text-to-Speech • Updated • 6
espnet/kan-bayashi_jsut_full_band_vits_prosody
Text-to-Speech • Updated • 9
espnet/kan-bayashi_jsut_tacotron2
Text-to-Speech • Updated • 10
espnet/kan-bayashi_jsut_full_band_vits_accent_with_pause
Text-to-Speech • Updated • 13
espnet/kan-bayashi_jsut_fastspeech2_accent_with_pause
Text-to-Speech • Updated • 6
espnet/kan-bayashi_jsut_fastspeech2
Text-to-Speech • Updated • 9
espnet/kan-bayashi_jsut_fastspeech2_accent
Text-to-Speech • Updated • 6
espnet/kan-bayashi_jsut_fastspeech
Text-to-Speech • Updated • 4
espnet/kan-bayashi_jsut_conformer_fastspeech2_transformer_prosody
Text-to-Speech • Updated • 6
espnet/kan-bayashi_jsut_conformer_fastspeech2_accent_with_pause
Text-to-Speech • Updated • 15
espnet/kan-bayashi_jsut_conformer_fastspeech2_tacotron2_prosody
Text-to-Speech • Updated • 6
espnet/kan-bayashi_jsut_conformer_fastspeech2_accent
Text-to-Speech • Updated • 12
espnet/kan-bayashi_jsut_conformer_fastspeech2
Text-to-Speech • Updated • 8
espnet/kan-bayashi_csmsc_vits
Text-to-Speech • Updated • 18
espnet/kan-bayashi_csmsc_tts_train_vits_raw_phn_pypinyin_g2p_phone_train.total_count.ave
Text-to-Speech • Updated • 8