MMAR: A Challenging Benchmark for Deep Reasoning in Speech, Audio, Music, and Their Mix
Paper
•
2505.13032
•
Published
•
3
Chen Yang
kiiic
·
AI & ML interests
Speech&MLLM
Recent Activity
authored
a paper
3 days ago
MOSS Transcribe Diarize: Accurate Transcription with Speaker Diarization
Organizations
