EEND

2000년 도입 · 논문 26편에서 사용

End-to-End Neural Diarization is a neural network for speaker diarization in which a neural network directly outputs speaker diarization results given a multi-speaker recording. To realize such an end-to-end model, the speaker diarization problem is formulated as a multi-label classification problem and a permutation-free objective function is introduced to directly minimize diarization errors. The EEND method can explicitly handle speaker overlaps during training and inference. Just by feeding multi-speaker recordings with corresponding speaker segment labels, the model can be adapted to real conversations.

출처: End-to-End Neural Diarization: Reformulating Speaker Diarization as Simple Multi-label Classification

소개 논문: End-to-End Neural Diarization: Reformulating Speaker Diarization as Simple Multi-label Classification