most citedAuxiliary Loss of Transformer with Residual Connection for End-to-End Speaker Diarization

1 citations · 1 across the 2 of their papers we have counts for

collaborators

2 papers

eess.AS2022

GIST-AiTeR System for the Diarization Task of the 2022 VoxCeleb Speaker Recognition Challenge

Dongkeon Park, Yechan Yu, Kyeong Wan Park +2

This report describes the submission system of the GIST-AiTeR team at the 2022 VoxCeleb Speaker Recognition Challenge (VoxSRC) Track 4. Our system mainly includes speech enhancemen…

eess.AS2021★ 1 cited

Auxiliary Loss of Transformer with Residual Connection for End-to-End Speaker Diarization

Yechan Yu, Dongkeon Park, Hong Kook Kim

End-to-end neural diarization (EEND) with self-attention directly predicts speaker labels from inputs and enables the handling of overlapped speech. Although the EEND outperforms c…