DIHARD III

DIHARD III is a benchmark dataset used to evaluate diarization error rates (DERs) in speaker diarization systems.

Papers using DIHARD III (10)

Pushing the Limits of End-to-End Diarization2025Exploring Speaker Diarization with Mixture of Experts2025Target-Speaker Voice Activity Detection via Sequence-to-Sequence Prediction2022 · 2 citesTowards Neural Diarization for Unlimited Numbers of Speakers Using Global and Local Attractors2021 · 1 citesAttention-based Encoder-Decoder End-to-End Neural Diarization with Embedding Enhancer2023 · 1 citesMulti-Input Multi-Output Target-Speaker Voice Activity Detection For Unified, Flexible, and Robust Audio-Visual Speaker Diarization2024 · 1 citesEnd-to-end Online Speaker Diarization with Target Speaker Tracking2023Speaker Embeddings With Weakly Supervised Voice Activity Detection For Efficient Speaker Diarization2024Self-Tuning Spectral Clustering for Speaker Diarization2024LS-EEND: Long-Form Streaming End-to-End Neural Diarization with Online Attractor Extraction2024