arxiv:2506.02863
Tiantian Feng
tiantiaf
AI & ML interests
Postdoc@USC SAIL Lab | Audio | Speech | Multi-modal | Affective Computing | Time-series | Federated Learning
Recent Activity
authored
a paper
36 minutes ago
CapSpeech: Enabling Downstream Applications in Style-Captioned
Text-to-Speech
upvoted
a
paper
6 days ago
CapSpeech: Enabling Downstream Applications in Style-Captioned
Text-to-Speech
liked
a dataset
6 days ago
OpenSound/CapSpeech_Emilia
Organizations
None yet
Papers
2
models
11
tiantiaf/whisper-large-v3-narrow-accent
Audio Classification
•
Updated
•
546
•
3
tiantiaf/whisper-large-v3-msp-podcast-emotion
Audio Classification
•
Updated
•
600
•
3
tiantiaf/wavlm-large-voice-quality
Audio Classification
•
Updated
•
54
•
1
tiantiaf/wavlm-large-narrow-accent
Audio Classification
•
Updated
•
90
•
1
tiantiaf/wavlm-large-age-sex
Audio Classification
•
Updated
•
436
tiantiaf/whisper-large-v3-speech-flow
Audio Classification
•
Updated
•
339
•
1
tiantiaf/wavlm-large-broader-accent
Audio Classification
•
Updated
•
48
•
2
tiantiaf/wavlm-large-speech-flow
Audio Classification
•
Updated
•
102
•
1
tiantiaf/wavlm-large-categorical-emotion
Audio Classification
•
Updated
•
89
•
1
tiantiaf/whisper-large-v3-voice-quality
Audio Classification
•
Updated
•
312
•
1
datasets
0
None public yet