emotion2vec: Self-Supervised Pre-Training for Speech Emotion Representation
Paper • 2312.15185 • Published
Ziyang Ma
BoJack
AI & ML interests
None yet
Recent Activity
new activity 15 days ago
BoJack/MMAE:Add audio-to-audio task category authored a paper 16 days ago
emotion2vec: Self-Supervised Pre-Training for Speech Emotion
Representation authored a paper 16 days ago
MMAR: A Challenging Benchmark for Deep Reasoning in Speech, Audio,
Music, and Their MixOrganizations
authored 4
papers 16 days ago
MMAR: A Challenging Benchmark for Deep Reasoning in Speech, Audio, Music, and Their Mix
Paper • 2505.13032 • Published • 4
Omni-Captioner: Data Pipeline, Models, and Benchmark for Omni Detailed Perception
Paper • 2510.12720 • Published • 2
MMAE: A Massive Multitask Audio Editing Benchmark
Paper • 2606.07229 • Published • 45
submitted a
paper to Daily Papers 16 days ago
authored a
paper 9 months ago