Skip to main content

Research Repository

Advanced Search

A Novel Speech Intelligibility Enhancement Model based on Canonical Correlation and Deep Learning

Hussain, Tassadaq; Diyan, Muhammad; Gogate, Mandar; Dashtipour, Kia; Adeel, Ahsan; Tsao, Yu; Hussain, Amir

Authors

Muhammad Diyan

Ahsan Adeel

Yu Tsao



Abstract

Current deep learning (DL) based approaches to speech intelligibility enhancement in noisy environments are often trained to minimise the feature distance between noise-free speech and enhanced speech signals. Despite improving the speech quality, such approaches do not deliver required levels of speech intelligibility in everyday noisy environments. Intelligibility-oriented (I-O) loss functions have recently been developed to train DL approaches for robust speech enhancement. Here, we formulate, for the first time, a novel canonical correlation based I-O loss function to more effectively train DL algorithms. Specifically, we present a canonical-correlation based short-time objective intelligibility (CC-STOI) cost function to train a fully convolutional neural network (FCN) model. We carry out comparative simulation experiments to show that our CC-STOI based speech enhancement framework outperforms state-of-the-art DL models trained with conventional distance-based and STOI-based loss functions, using objective and subjective evaluation measures for case of both unseen speakers and noises. Ongoing future work is evaluating the proposed approach for design of robust hearing-assistive technology.

Presentation Conference Type Conference Paper (Published)
Conference Name 2022 44th Annual International Conference of the IEEE Engineering in Medicine & Biology Society (EMBC)
Start Date Jul 11, 2022
End Date Jul 15, 2022
Online Publication Date Sep 8, 2022
Publication Date 2022
Deposit Date Apr 19, 2024
Publisher Institute of Electrical and Electronics Engineers
Pages 2581--2584
Series ISSN 2694-0604
Book Title 2022 44th Annual International Conference of the IEEE Engineering in Medicine & Biology Society (EMBC)
DOI https://doi.org/10.1109/embc48229.2022.9871113
Public URL http://researchrepository.napier.ac.uk/Output/3597136