Diarization and separation based on a data-driven simplex

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review


Separation of underdetermined speech mixtures, where the number of speakers is greater than the number of microphones, is a challenging task. Due to the intermittent behaviour of human conversations, typically, the instantaneous number of active speakers does not exceed the number of microphones, namely the mixture is locally (over-)determined. This scenario is addressed in this paper using a dual stage approach: diarization followed by separation. The diarization stage is based on spectral decomposition of the correlation matrix between different time frames. Specifically, the spectral gap reveals the overall number of speakers, and the computed eigenvectors form a simplex of the activity of the speakers across time. In the separation stage, the diarization results are utilized for estimating the mixing acoustic channels, as well as for constructing an unmixing scheme for extracting the individual speakers. The performance is demonstrated in a challenging scenario with six speakers and only four microphones. The proposed method shows perfect recovery of the overall number of speakers, close to perfect diarization accuracy, and high separation capabilities in various reverberation conditions.

Original languageEnglish
Title of host publication2018 26th European Signal Processing Conference, EUSIPCO 2018
Number of pages5
ISBN (Electronic)9789082797015
StatePublished - 29 Nov 2018
Externally publishedYes
Event26th European Signal Processing Conference, EUSIPCO 2018 - Rome, Italy
Duration: 3 Sep 20187 Sep 2018

Publication series

NameEuropean Signal Processing Conference


Conference26th European Signal Processing Conference, EUSIPCO 2018


  • Blind audio source separation (BASS)
  • Diarization
  • Relative transfer function (RTF)
  • Simplex

All Science Journal Classification (ASJC) codes

  • Signal Processing
  • Electrical and Electronic Engineering


Dive into the research topics of 'Diarization and separation based on a data-driven simplex'. Together they form a unique fingerprint.

Cite this