Adaptive line enhancer for nonstationary harmonic noise reduction. (November 2021)

• Record Type: Journal Article
• Authors: Atkins, Aviva; Cohen, Israel; Benesty, Jacob
• Is Part Of: Computer speech & language. Volume 70(2021)
• Publication Date: 2021-11
• Subjects: Speech enhancement -- Noise reduction -- Single channel -- Adaptive line enhancer -- Nonstationary noise; Speech processing systems -- Periodicals; Automatic speech recognition -- Periodicals; Computers -- Periodicals; Linguistics -- Periodicals; Speech-Language Pathology -- Periodicals; Traitement automatique de la parole -- Périodiques; Reconnaissance automatique de la parole -- Périodiques; Automatic speech recognition; Speech processing systems; Electronic journals; Periodicals; 006.454
• DOI: 10.1016/j.csl.2021.101245
• Languages: English
• ISSNs: 0885-2308

Abstract

Highlights: Frequency-domain adaptive line enhancer for nonstationary harmonic noise reduction. Combination of forward and backward linear filters based on minimal spectral error. Combined filter applied together with harmonic noise presence indicator. Increased reduction span of the noise transient using the combined filter. Improved perceptual speech quality and intelligibility for single channel. Abstract: In this paper, we propose a frequency-domain adaptive line enhancer (ALE) to reduce nonstationary harmonic noise, such as medical equipment beeps, from a noisy speech signal captured by a single microphone. The reduction of nonstationary noise is very challenging, with the tradeoff between noise reduction and speech distortion, often resulting with much noise residuals. The proposed ALE is a combination of the commonly-used forward adaptive linear filter and a non-causal backward adaptive linear filter used together with an indicator for the presence of transient noise. The proposed combined filter results in less noise residuals while preserving the speech components. We compare the proposed approach to conventional and recent methods, and show that it can outperform these methods, achieving lower distortion, more noise reduction, and overall better speech quality and intelligibility.