Introduces the ACII-DaiKon benchmark with three sub-challenges on directional influence, turn-taking, and rapport prediction using 945 dyadic conversations across five languages.
Robust speech recognition via large-scale weak supervision
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2representative citing papers
DoWhatISay provides spoken and written prompt variants across tasks and languages for SLLM evaluation, showing text prompts outperform spoken ones except in speech-output tasks.
citing papers explorer
-
The 2026 ACII Dyadic Conversations (DaiKon) Workshop & Challenge
Introduces the ACII-DaiKon benchmark with three sub-challenges on directional influence, turn-taking, and rapport prediction using 945 dyadic conversations across five languages.
-
Do What I Say: A Spoken Prompt Dataset for Instruction-Following
DoWhatISay provides spoken and written prompt variants across tasks and languages for SLLM evaluation, showing text prompts outperform spoken ones except in speech-output tasks.