Real-Time Joint Noise Suppression and Bandwidth Extension of Noisy Reverberant Wideband Speech

Loading...
Thumbnail Image

Access rights

openAccess
acceptedVersion

URL

Journal Title

Journal ISSN

Volume Title

A4 Artikkeli konferenssijulkaisussa

Date

2024-10-04

Major/Subject

Mcode

Degree programme

Language

en

Pages

5

Series

2024 18th International Workshop on Acoustic Signal Enhancement (IWAENC), pp. 6-10, International Workshop on Acoustic Signal Enhancement

Abstract

Artificially extending the bandwidth of speech in real-time applications that are band-limited to 16 kHz (known as wideband) or lower sample rates such as VoIP or communication over Bluetooth, can significantly improve its perceptual quality. Typically, dry clean speech is assumed as input to estimate the missing spectral information. However, such an assumption falls short if the input speech is reverberant or has been contaminated by noise, resulting in audible artifacts. We propose a real-time low-complexity multitasking neural network capable of performing noise suppression and bandwidth extension from 16 kHz to 48 kHz (fullband) on a CPU, preventing such issues even if the noise cannot be completely removed from the input. Instead of employing a monolithic model, we adopt a modular approach and complexity reduction methods that result in a more compact model than the sum of its parts while improving its performance.

Description

Keywords

Bandwidth extension, Deep learning, Multitasking, Noise suppression, Real-time, deep learning, noise suppression, real-time, multitasking

Other note

Citation

Gómez Mellado, E & Bäckström, T 2024, Real-Time Joint Noise Suppression and Bandwidth Extension of Noisy Reverberant Wideband Speech . in 2024 18th International Workshop on Acoustic Signal Enhancement (IWAENC) . International Workshop on Acoustic Signal Enhancement, IEEE, pp. 6-10, International Workshop on Acoustic Signal Enhancement, Aalborg, Denmark, 09/09/2024 . https://doi.org/10.1109/IWAENC61483.2024.10694458