A Simple Correlation-Based Model of Intelligibility for Nonlinear Speech Enhancement and Separation

Jesper Boldt, Daniel P. W. Ellis

Publikation: Bidrag til bog/antologi/rapport/konference proceedingKonferenceartikel i proceedingForskningpeer review

37 Citationer (Scopus)
361 Downloads (Pure)

Abstract

Applying a binary mask to a pure noise signal can result in speech
that is highly intelligible, despite the absence of any of the target
speech signal. Therefore, to estimate the intelligibility benefit of
highly nonlinear speech enhancement techniques, we contend that
SNR is not useful; instead we propose a measure based on the simi-
larity between the time-varying spectral envelopes of target speech
and system output, as measured by correlation. As with previous
correlation-based intelligibility measures, our system can broadly
match subjective intelligibility for a range of enhanced signals. Our
system, however, is notably simpler and we explain the practical
motivation behind each stage. This measure, freely available as a
small Matlab implementation, can provide a more meaningful eval-
uation measure for nonlinear speech enhancement systems, as well
as providing a transparent objective function for the optimization of
such systems.
OriginalsprogEngelsk
TitelProceedings of the 17th European Signal Processing Conference (EUSIPCO-2009)
Antal sider5
ForlagEURASIP
Publikationsdato2009
StatusUdgivet - 2009
BegivenhedEuropean Signal Processing Conference - Glasgow, Storbritannien
Varighed: 24 aug. 200928 aug. 2009
Konferencens nummer: 17

Konference

KonferenceEuropean Signal Processing Conference
Nummer17
Land/OmrådeStorbritannien
ByGlasgow
Periode24/08/200928/08/2009

Bibliografisk note

Online proceedings

Fingeraftryk

Dyk ned i forskningsemnerne om 'A Simple Correlation-Based Model of Intelligibility for Nonlinear Speech Enhancement and Separation'. Sammen danner de et unikt fingeraftryk.

Citationsformater