Skip to Main content Skip to Navigation
Conference papers

Linguistic influences on bottom-up and top-down clustering for speaker diarization

Abstract : While bottom-up approaches have emerged as the standard, default approach to clustering for speaker diarization we have always found the top-down approach gives equivalent or superior performance. Our recent work shows that significant gains in performance can be obtained when cluster purification is applied to the output of topdown systems but that it can degrade performance when applied to the output of bottom-up systems. This paper demonstrates that these observations can be accounted for by factors unrelated to the speaker and that they can impact more strongly on the performance of bottom-up clustering strategies than top-down strategies. Experimental results confirm that clusters produced through top-down clustering are better normalized against phone variation than those produced through bottom-up clustering and that this accounts for the observed inconsistencies in purification performance. The work highlights the need for marginalization strategies which should encourage convergence toward different speakers rather than toward nuisance factors such as that those related to the linguistic content.
Document type :
Conference papers
Complete list of metadata

Cited literature [14 references]  Display  Hide  Download

https://hal.archives-ouvertes.fr/hal-00733392
Contributor : Simon Bozonnet Connect in order to contact the contributor
Submitted on : Tuesday, September 18, 2012 - 3:26:32 PM
Last modification on : Wednesday, July 8, 2020 - 9:10:03 AM
Long-term archiving on: : Wednesday, December 19, 2012 - 3:45:27 AM

File

LINGUISTIC_INFLUENCES_ON_BOTTO...
Files produced by the author(s)

Identifiers

  • HAL Id : hal-00733392, version 1

Collections

Citation

Simon Bozonnet, Dong Wang, Nicholas Evans, Raphaël Troncy. Linguistic influences on bottom-up and top-down clustering for speaker diarization. ICASSP 2011, May 2011, Prague, Czech Republic. pp.1. ⟨hal-00733392⟩

Share

Metrics

Les métriques sont temporairement indisponibles