The University of Southampton
University of Southampton Institutional Repository
Warning ePrints Soton is experiencing an issue with some file downloads not being available. We are working hard to fix this. Please bear with us.

Non-intrusive speech intelligibility prediction using automatic speech recognition derived measures

Non-intrusive speech intelligibility prediction using automatic speech recognition derived measures
Non-intrusive speech intelligibility prediction using automatic speech recognition derived measures
The estimation of speech intelligibility is still far from being a solved problem. Especially one aspect is problematic: most of the standard models require a clean reference signal in order to estimate intelligibility. This is an issue of some significance, as a reference signal is often un- available in practice. In this work, therefore a non-intrusive speech intelligibility estimation framework is presented. In it, human listeners’ performance in keyword recognition tasks is predicted using intelligibility measures that are derived from models trained for automatic speech recognition (ASR). One such ASR-based and one signal-based measure are combined into a full framework, the proposed NO-Reference Intelligibility (Nori) estimator, which is evaluated in predicting the performance of both normal-hearing and hearing-impaired listen- ers in multiple noise conditions. It is shown that the Nori framework even outperforms the widely used reference-based (or intrusive) short-term objective intelligibility (STOI) measure in most considered scenarios, while being applicable in fully blind scenarios with no reference signal or transcription, creating perspectives for online and personalized optimization of speech enhancement systems.
Bleeck, Stefan
c888ccba-e64c-47bf-b8fa-a687e87ec16c
Karbasi, Mahdie
b94be01f-0b7a-445e-ad69-ef4f18024465
Kolossa, Dorothea
b866cffc-9c55-4e9c-a298-4e24d890f8f4
Bleeck, Stefan
c888ccba-e64c-47bf-b8fa-a687e87ec16c
Karbasi, Mahdie
b94be01f-0b7a-445e-ad69-ef4f18024465
Kolossa, Dorothea
b866cffc-9c55-4e9c-a298-4e24d890f8f4

Bleeck, Stefan, Karbasi, Mahdie and Kolossa, Dorothea (2020) Non-intrusive speech intelligibility prediction using automatic speech recognition derived measures. arXiv.

Record type: Article

Abstract

The estimation of speech intelligibility is still far from being a solved problem. Especially one aspect is problematic: most of the standard models require a clean reference signal in order to estimate intelligibility. This is an issue of some significance, as a reference signal is often un- available in practice. In this work, therefore a non-intrusive speech intelligibility estimation framework is presented. In it, human listeners’ performance in keyword recognition tasks is predicted using intelligibility measures that are derived from models trained for automatic speech recognition (ASR). One such ASR-based and one signal-based measure are combined into a full framework, the proposed NO-Reference Intelligibility (Nori) estimator, which is evaluated in predicting the performance of both normal-hearing and hearing-impaired listen- ers in multiple noise conditions. It is shown that the Nori framework even outperforms the widely used reference-based (or intrusive) short-term objective intelligibility (STOI) measure in most considered scenarios, while being applicable in fully blind scenarios with no reference signal or transcription, creating perspectives for online and personalized optimization of speech enhancement systems.

Text
mahdie-speech - Author's Original
Download (803kB)

More information

Published date: 16 October 2020

Identifiers

Local EPrints ID: 444947
URI: http://eprints.soton.ac.uk/id/eprint/444947
PURE UUID: 9befbe4e-553c-414c-85e6-d6062cc57e92
ORCID for Stefan Bleeck: ORCID iD orcid.org/0000-0003-4378-3394

Catalogue record

Date deposited: 12 Nov 2020 17:33
Last modified: 08 Sep 2021 01:41

Export record

Contributors

Author: Stefan Bleeck ORCID iD
Author: Mahdie Karbasi
Author: Dorothea Kolossa

Download statistics

Downloads from ePrints over the past year. Other digital versions may also be available to download e.g. from the publisher's website.

View more statistics

Atom RSS 1.0 RSS 2.0

Contact ePrints Soton: eprints@soton.ac.uk

ePrints Soton supports OAI 2.0 with a base URL of http://eprints.soton.ac.uk/cgi/oai2

This repository has been built using EPrints software, developed at the University of Southampton, but available to everyone to use.

We use cookies to ensure that we give you the best experience on our website. If you continue without changing your settings, we will assume that you are happy to receive cookies on the University of Southampton website.

×