SCB: SpeechConversationBench for Evaluating Multi-Turn Reasoning in Speech-to-Speech Models
Speech-to-speech systems must solve tasks whose requirements emerge across conversational turns. We introduce SpeechConversationBench (SCB), a focused evaluation of spoken mathematical reasoning using 103 sharded GSM8K problems. The framework compares the original problem delivered in one turn (full), its concatenated information shards delivered together (concat), and incremental spoken…
We haven't written up this one. arXiv cs.AI has the full story — the link below goes straight to it.