Speech Enhancement

Research Article Cover Portal

Evaluation of Speech Enhancement Techniques and Signal Processing for Intelligibility in Environmental Noise

Biomedical Engineering Biosensors Research Group — University of Connecticut

Abstract & Study Overview

This research evaluates the efficacy of advanced signal processing algorithms designed to improve speech perception in high-noise environments. Participants will engage in an audio matrix task to measure baseline speech reception thresholds. The data gathered aims to optimize assistive listening profiles and engineering metrics for next-generation hearing protection systems.

Journal Articles

Soleymanpour, R., Soleymanpour, M., Brammer, A. J., Johnson, M. T., Kim, I. (2023). Speech Enhancement Algorithm based on a Convolutional Neural Network Reconstruction of the Temporal Envelope of Speech in Noisy Environments. IEEE Access, 11, 5328-5336.

Summary: This paper introduces an innovative speech-enhancement strategy that leverages an embedded convolutional neural network (CNN) to reconstruct subband temporal envelopes across 16 parallel frequency bands to recover crucial speech patterns from environmental noise.

View Article Access Code →

Soleymanpour, R., Brammer, A. J., Marquis, H., Heiney, E., Kim, I. (2022). Enhancement of Speech in Noise using Multi-channel, time-varying Gains Derived from the Temporal Envelope. Applied Acoustics, 190, 108634.

Summary: This study evaluates a method of using multi-channel, time-varying acoustic gains controlled by the temporal envelope to reduce noise artifacts and analyze target thresholds required to optimize wearable hearing systems.

View Article Access Code →

Conference Presentations

AJ Brammer, R Soleymanpour, K Golzari, E Heiney, H Marquis, I Kim (2024, March). Improving speech understanding for face-to-face communication in noise when wearing hearing protectors. Presented at The Journal of the Acoustical Society of America Meeting.

View Citation Record →

AJ Brammer, K Golzari, R Soleymanpour, E Heiney, H Marquis, I Kim (2024, March). Self-administered, internet-enabled, modified rhyme test (MRT) for evaluating consonant confusion in remote subjects. Presented at The Journal of the Acoustical Society of America Meeting.

View Citation Record →

R Soleymanpour, K Golzari, I Kim, E Heiney, H Marquis, A J. Brammer (2021, October). Using ideal binary masking based on signal-to-noise ratio of temporal amplitude envelope to improve the intelligibility of speech in noise. Presented at The Journal of the Acoustical Society of America Meeting.

View Citation Record →

R Soleymanpour, A J. Brammer, I Kim (2020, October). Effect of envelope signal-to-noise ratio on the intelligibility of speech in speech-spectrum shaped noise. Presented at The Journal of the Acoustical Society of America Meeting.

View Citation Record →

R Soleymanpour, A J. Brammer, I Kim (2020, October). Investigation of a temporal modulation based method on the intelligibility of speech in speech-spectrum shaped noise. Presented at The Journal of the Acoustical Society of America Meeting.

View Citation Record →

Patents

Brammer, A.J., & Kim, I. (2025). Method and apparatus for improving intelligibility of speech and audibility of warning sound in noise. U.S. Patent Publication No. 2025/0022481 A1. Assignee: University of Connecticut.