The Second DIHARD Diarization Challenge: Dataset, task, and baselines
This addresses the problem of making speaker diarization systems more reliable for researchers and practitioners in speech processing, but it is incremental as it builds on a previous challenge.
The paper introduces the second DIHARD challenge, which aims to improve speaker diarization robustness across varied recording conditions and domains, and describes its design, datasets, and baseline systems.
This paper introduces the second DIHARD challenge, the second in a series of speaker diarization challenges intended to improve the robustness of diarization systems to variation in recording equipment, noise conditions, and conversational domain. The challenge comprises four tracks evaluating diarization performance under two input conditions (single channel vs. multi-channel) and two segmentation conditions (diarization from a reference speech segmentation vs. diarization from scratch). In order to prevent participants from overtuning to a particular combination of recording conditions and conversational domain, recordings are drawn from a variety of sources ranging from read audiobooks to meeting speech, to child language acquisition recordings, to dinner parties, to web video. We describe the task and metrics, challenge design, datasets, and baseline systems for speech enhancement, speech activity detection, and diarization.