SpeakerSleuth: Evaluating Large Audio-Language Models as Judges for Multi-turn Speaker Consistency

arXiv:2601.04029v1 Announce Type: new Abstract: Large Audio-Language Models (LALMs) as judges have emerged as a prominent approach for evaluating speech generation quality, yet their ability to assess speaker consistency across multi-turn conversations remains unexplored. We present SpeakerSleuth, …