ODESSA at Albayzin Speaker Diarization Challenge 2018 - Archive ouverte HAL Access content directly
Conference Papers Year : 2018

ODESSA at Albayzin Speaker Diarization Challenge 2018

Abstract

This paper describes the ODESSA submissions to the Albayzin Speaker Diarization Challenge 2018. The challenge addresses the diarization of TV shows. This work explores three different techniques to represent speech segments, namely binary key, x-vector and triplet-loss based embeddings. While training-free methods such as the binary key technique can be applied easily to a scenario where training data is limited, the training of robust neural-embedding extractors is considerably more challenging. However, when training data is plentiful (open-set condition), neural embeddings provide more robust segmentations, giving speaker representations which lead to better diarization performance. The paper also reports our efforts to improve speaker diarization performance through system combination. For systems with a common temporal resolution, fusion is performed at segment level during clustering. When the systems under fusion produce segmentations with an arbitrary resolution, they are combined at solution level. Both approaches to fusion are shown to improve diarization performance.
No file

Dates and versions

hal-01987808 , version 1 (21-01-2019)

Identifiers

  • HAL Id : hal-01987808 , version 1

Cite

Jose Patino, Héctor Delgado, Ruiqing Yin, Hervé Bredin, Claude Barras, et al.. ODESSA at Albayzin Speaker Diarization Challenge 2018. IberSPEECH 2018, 2018, Barcelona, Spain. pp.211--215. ⟨hal-01987808⟩
68 View
0 Download

Share

Gmail Facebook Twitter LinkedIn More