Non-Intrusive Intelligibility Prediction Using a Codebook-Based Approach

Research output: Contribution to journalConference article in Journal

Abstract

It could be beneficial for users of hearing aids if
these were able to automatically adjust the processing according
to the speech intelligibility in the specific acoustic environment.
Most speech intelligibility metrics are intrusive, i.e., they require
a clean reference signal, which is rarely available in real-life
applications. This paper proposes a method, which allows using
an intrusive short-time objective intelligibility (STOI) metric
without requiring access to a clean signal. The clean speech
reference signal is replaced by the clean speech envelope spectrum
estimated from the noisy signal. The spectral envelope has been
shown to be an important cue for speech intelligibility and is used
as the reference signal inside STOI. The spectral envelopes are
estimated as a combination of predefined dictionaries, i.e., codebooks,
that best fits the noisy speech signal. The simulations show
a high correlation between the proposed non-intrusive codebookbased
STOI (NIC-STOI) and the intrusive STOI indicating that
NIC-STOI is a suitable metric for automatic classification of
speech signals
Close

Details

It could be beneficial for users of hearing aids if
these were able to automatically adjust the processing according
to the speech intelligibility in the specific acoustic environment.
Most speech intelligibility metrics are intrusive, i.e., they require
a clean reference signal, which is rarely available in real-life
applications. This paper proposes a method, which allows using
an intrusive short-time objective intelligibility (STOI) metric
without requiring access to a clean signal. The clean speech
reference signal is replaced by the clean speech envelope spectrum
estimated from the noisy signal. The spectral envelope has been
shown to be an important cue for speech intelligibility and is used
as the reference signal inside STOI. The spectral envelopes are
estimated as a combination of predefined dictionaries, i.e., codebooks,
that best fits the noisy speech signal. The simulations show
a high correlation between the proposed non-intrusive codebookbased
STOI (NIC-STOI) and the intrusive STOI indicating that
NIC-STOI is a suitable metric for automatic classification of
speech signals
Original languageEnglish
JournalProceedings of the European Signal Processing Conference (EUSIPCO)
ISSN2076-1465
DOI
StatePublished - 2017
Publication categoryResearch
Peer-reviewedYes
Event25th European Signal Processing Conference 2017 - Kos International Convention Center, Kos, Greece
Duration: 28 Aug 20172 Sep 2017
Conference number: 25
https://www.eusipco2017.org/#

Conference

Conference25th European Signal Processing Conference 2017
Number25
LocationKos International Convention Center
CountryGreece
CityKos
Period28/08/201702/09/2017
Internet address

Map

ID: 266074572