Noise reduction of speech signals using time-varying and multi-band adaptive gain control for smart digital hearing protectors

Lezzoum, Narimene; Gagnon, Ghyslain; Voix, Jérémie

doi:10.1016/j.apacoust.2016.03.001

Cited by 7 publications

(1 citation statement)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Thus, manipulation of the TEV can be considered potentially an effective approach for enhancing speech quality as well as intelligibility [11][18]- [20]. According to Lezzoum et al, using the TEV as time-varying gains can help improve speech quality in noisy environments [21]. While this method effectively reduces noise, it has limited capability to improve speech intelligibility in noisy conditions, because it cannot detect speech components or correctly reconstruct the TEV [22] [23].…”

Section: Introductionmentioning

confidence: 99%

Speech Enhancement Algorithm Based on a Convolutional Neural Network Reconstruction of the Temporal Envelope of Speech in Noisy Environments

Soleymanpour

Brammer

et al. 2023

IEEE Access

View full text Add to dashboard Cite

Temporal modulation processing is a promising technique for improving the intelligibility and quality of speech in noise. We propose a speech enhancement algorithm to construct the temporal envelope (TEV) in the time-frequency domain by means of an embedded convolutional neural network (CNN). To accomplish this, the input speech signals are divided into sixteen parallel frequency bands (subbands) with bandwidths approximating 1.5 times that of auditory filters. The corrupted TEVs in each subband are extracted and then fed to the 1-dimensional CNN (1-D CNN) model to restore the TEVs distorted by noise. The method is evaluated using 2,700 words from nine different talkers, which are mixed with speech-spectrum shaped random noise (SSN), and babble noise, at different signal-to-noise ratios. The Short-time Objective Intelligibility (STOI) and Perceptual Evaluation of Speech Quality (PESQ) metrics are used to evaluate the performance of the 1-D CNN algorithm. Results suggest that the 1-D CNN model improves STOI scores by 27% and 34% for SSN and babble noise, respectively, and PESQ scores by 19% and 17%, respectively, compared to a conventional TEV-based speech enhancement algorithm.

show abstract