audio-llm

#audio-llm

@Chenyang_Lyu: Excited to publicly release LongSpeech, which will be presented at #ICASSP2026 ! Most Audio LLMs are at short audio but…

X AI KOLs Following ↗ · 2026-04-21

Researchers release LongSpeech, a 100k-segment dataset of ~10-min clips to benchmark long-form audio understanding across 8 tasks, to be presented at ICASSP 2026.

0 favorites 0 likes

audio-llm

@Chenyang_Lyu: Excited to publicly release LongSpeech, which will be presented at #ICASSP2026 ! Most Audio LLMs are at short audio but…

Submit Feedback