Skip to Main content Skip to Navigation
Conference papers

End-to-end speaker segmentation for overlap-aware resegmentation

Abstract : Speaker segmentation consists in partitioning a conversation between one or more speakers into speaker turns. Usually addressed as the late combination of three sub-tasks (voice activity detection, speaker change detection, and overlapped speech detection), we propose to train an end-to-end segmentation model that does it directly. Inspired by the original end-to-end neural speaker diarization approach (EEND), the task is modeled as a multi-label classification problem using permutation-invariant training. The main difference is that our model operates on short audio chunks (5 seconds) but at a much higher temporal resolution (every 16ms). Experiments on multiple speaker diarization datasets conclude that our model can be used with great success on both voice activity detection and overlapped speech detection. Our proposed model can also be used as a post-processing step, to detect and correctly assign overlapped speech regions. Relative diarization error rate improvement over the best considered baseline (VBx) reaches 17% on AMI, 13% on DIHARD 3, and 13% on VoxConverse.
Complete list of metadata

https://hal-univ-lemans.archives-ouvertes.fr/hal-03257524
Contributor : Antoine Laurent Connect in order to contact the contributor
Submitted on : Friday, June 11, 2021 - 8:48:06 AM
Last modification on : Tuesday, October 19, 2021 - 2:23:26 PM
Long-term archiving on: : Sunday, September 12, 2021 - 6:19:52 PM

File

2104.04045.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-03257524, version 1
  • ARXIV : 2104.04045

Citation

Hervé Bredin, Antoine Laurent. End-to-end speaker segmentation for overlap-aware resegmentation. Interspeech 2021, Aug 2021, Brno, Czech Republic. ⟨hal-03257524⟩

Share

Metrics

Record views

125

Files downloads

56