Skip to content
Open access

A deep residual complex learning framework with long-range temporal context for phase-aware speech enhancement

Aug 2026 · Engineering Research Express · Vol 8 · 0 citations · 22 references
Physics

TL;DR

Analysis of the results indicates that this multi-objective optimization framework achieves superior speech enhancement by simultaneously addressing magnitude and phase reconstruction, waveform-level distortion, and psychoacoustic naturalness, a balance not achieved in any prior works so far.

Abstract

In this paper, we propose an advanced speech enhancement model capable of effectively separating clean speech from noisy audio signals. The primary objective here is to improve speech intelligibility and quality in noisy environments while preserving critical speech components. We propose a GAN based novel residual learning architecture with long range temporal context using complex spectrograms. This is achieved by combining residual neural networks with dilated temporal processing. The model processes both magnitude and phase components in the time-frequency domain, implementing residual learning for stable training and a dilated temporal module to capture long-range dependencies in speech signals. Experiments were conducted on benchmark of VoiceBank-DEMAND dataset under various noise conditions. During experimentation, the proposed model demonstrated superior performance compared to existing ones, achieving 3.43 dB improvement in perceptual evaluation of speech quality measurement. The novelties include a phase-aware complex masking system which jointly optimizes magnitude and phase for more natural-sounding output and incorporation of a Dilated temporal module. This module further expands receptive fields exponentially in order to model speech dynamics without increasing parameters drastically. Residual architecture also balances deep feature extraction, computational efficiency and the composite loss function that uniquely combine in delivering superior results. Analysis of our results indicates that this multi-objective optimization framework achieves superior speech enhancement by simultaneously addressing magnitude and phase reconstruction, waveform-level distortion, and psychoacoustic naturalness, a balance not achieved in any prior works so far.

Read PDF

Similar papers

Conference Aug 2026

High-Fidelity Speech Reconstruction Architectures Utilizing Spectral Attention and Temporal Memory Units to Enhance Robust Signal Quality

This paper introduces a high-fidelity speech reconstruction system that enhances speech quality and robustness even in challenging environments. The introduced model comprises a Spectral Attention and a Temporal Memory Unit that improve spectral and temporal representations of the speech signal, respectively. The Spect...

Anjali Goswami, Anjali Krushna Kadao · 0 citations
Open access Aug 2026

Single-Channel Speech Enhancement Method Based on Deep Neural Networks

In practical voice communication and processing, speech signals are extremely sensitive to background noise, equipment noise, and interference from complex environments, leading to a decline in speech quality and clarity. This, in turn, affects the overall performance of downstream systems such as speech recognition, s...

Wen Fan, Wei-Yu Liang, Duo-Duo Han et al. · 0 citations
Open access Sep 2026

Speech intelligibility comparison of standalone and two-stage deep learning architectures for behind-the-ear-to-binaural enhancement

Unlike the original hypothesis, the standalone U-Net performed better in keyword recognition than the speech-target-oriented two-stage model, emphasizing the need for perceptual validation in evaluating speech-processing systems.

R. Viveros-Muñoz, Carla E. Contreras-Saavedra, Sebastián Guajardo-Herrera et al. · 0 citations
Open access Aug 2026

Efficient speech denoising using CleanUNet optimized with Mamba and hybrid spectral loss

An optimized version of CleanUNet is proposed that significantly reduces model complexity while maintaining competitive performance, and replaces the original Transformer bottleneck with a Mamba module, which offers efficient sequence modeling with linear time complexity.

Matheus Vieira da Silva, João Fernando Mari, A. Backes · 0 citations
Review Open access Sep 2026

Advances in Speech Enhancement: A Comprehensive Review of Noise Suppression Techniques

Overall, this review provides a unified perspective on speech enhancement techniques, identifies their strengths, and highlights emerging research opportunities for the development of robust, efficient, and intelligent speech enhancement systems.

Pushpraj Tanwar, A. Somkuwar, Rakesh Kumar Gumasta · 0 citations
Sep 2026

A dual-stream spectral network for versatile full-band speech enhancement.

Evaluation results demonstrate that DSVN improves restoration quality under both single- and mixed-degradation scenarios, and shows clear advantages in non-intrusive quality assessment, spectral distance, and automatic speech recognition evaluation, indicating that the enhanced speech is not only cleaner but also more...

Jun-Kang Yang, Hiromitsu Nishizaki, C. Leow et al. · 0 citations

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.