A Supervised Approach to Global Signal-to-Noise Ratio Estimation for Whispered and Pathological Voices


The presence of background noise in signals adversely affects the performance of many speech-based algorithms. Accurate estimation of signal-to-noise-ratio (SNR), as a measure of noise level in a signal, can help in compensating for noise effects. Most existing SNR estimation methods have been developed for normal speech and might not provide accurate estimation for special speech types such as whispered or disordered voices, particularly, when they are corrupted by non-stationary noises. In this paper, we first investigate the impact of stationary and non-stationary noise on the behavior of mel-frequency cepstral coefficients (MFCCs) extracted from normal, whispered and pathological voices. We demonstrate that, regardless of the speech type, the mean and the covariance of MFCCs are predictably modified by additive noise and the amount of change is related to the noise level. Then, we propose a new supervised method for SNR estimation which is based on a regression model trained on MFCCs of the noisy signals. Experimental results show that the proposed approach provides accurate estimation and consistent performance for various speech types under different noise conditions.

Publication DOI: https://doi.org/10.1109/ICASSP.2018.8462459
Divisions: Engineering & Applied Sciences > Systems analytics research institute (SARI)
Engineering & Applied Sciences > Mathematics
Additional Information: © 2018 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.
Event Title: 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
Event Type: Other
Event Dates: 2018-04-15 - 2018-04-20
ISBN: 978-1-5386-4659-5, 978-1-5386-4658-8
Full Text Link:
Related URLs: https://ieeexpl ... rce=SEARCHALERT (Publisher URL)
PURE Output Type: Conference contribution
Published Date: 2018-09-13
Accepted Date: 2018-01-29
Authors: Poorjam, Amir Hossein
Little, Max A ( 0000-0002-1507-3822)
Jensen, Jesper Rindom
Christensen, Mads Græsbøll



Version: Accepted Version

| Preview

Export / Share Citation


Additional statistics for this record