Solving global permutation ambiguity of time domain BSS using speaker specific features of speech signals - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Conference Papers Year : 2009

Solving global permutation ambiguity of time domain BSS using speaker specific features of speech signals

Abstract

Multidimensional localization of multiple sources using BSS based TDOA estimators, requires the solution of global permutation ambiguity before fusing several TDOA estimations. Since the separation quality of BSS isn't always perfect, it is not easy to decide which TDOA belongs to which source. Here we study the possibility of using several speaker specific features of speech signal in order to recognize perceptually dominant sources in each one of moderately separated outputs of BSS algorithm. We compare the feasibility of different features in terms of validity rate of decisions and computational complexity.

Domains

Sound [cs.SD]
Fichier principal
Vignette du fichier
vk2.pdf (251.35 Ko) Télécharger le fichier
Origin : Files produced by the author(s)
Loading...

Dates and versions

hal-00938356 , version 1 (29-01-2014)

Identifiers

  • HAL Id : hal-00938356 , version 1

Cite

Vahid Khanagha, Ali Khanagha. Solving global permutation ambiguity of time domain BSS using speaker specific features of speech signals. 2009 IEEE Symposium on Industrial Electronics and Applications (ISIEA 2009), IEEE, Oct 2009, Kuala Lumpur, Malaysia. ⟨hal-00938356⟩
62 View
244 Download

Share

Gmail Facebook X LinkedIn More