The Speed Submission to DIHARD II: Contributions & Lessons Learned - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Preprints, Working Papers, ... Year :

The Speed Submission to DIHARD II: Contributions & Lessons Learned

Abstract

This paper describes the speaker diarization systems developed for the Second DIHARD Speech Diarization Challenge (DIHARD II) by the Speed team. Besides describing the system, which considerably outperformed the challenge baselines, we also focus on the lessons learned from numerous approaches that we tried for single and multi-channel systems. We present several components of our diarization system, including categorization of domains, speech enhancement, speech activity detection, speaker embeddings, clustering methods, resegmentation, and system fusion. We analyze and discuss the effect of each such component on the overall diarization performance within the realistic settings of the challenge.
Fichier principal
Vignette du fichier
Speed_DIHARDII_Manuscript.pdf (210.8 Ko) Télécharger le fichier
Origin : Files produced by the author(s)
Loading...

Dates and versions

hal-02352840 , version 1 (07-11-2019)
hal-02352840 , version 2 (30-06-2020)

Identifiers

  • HAL Id : hal-02352840 , version 2

Cite

Md Sahidullah, Jose Patino, Samuele Cornell, Ruiqing Yin, Sunit Sivasankaran, et al.. The Speed Submission to DIHARD II: Contributions & Lessons Learned. 2019. ⟨hal-02352840v2⟩
139 View
445 Download

Share

Gmail Facebook Twitter LinkedIn More