arXiv subjects

Mohamed Elminshawi

Publications and source records attributed to Mohamed Elminshawi.

8 recordsLinked to original sources

arXiv2026

SlimDiffuSE: Towards Efficient Diffusion-Based Speech Enhancement using Slimmable Networks

Diffusion-based models are emerging in the speech enhancement domain and are achieving state-of-the-art performance across various benchmark datasets. A major downside of diffusion models is that data generation requires many evaluations of a typically large neural network, which results in high overall complexity. In this work, we propose a slimmable diffusion model that employs adaptive network widths throughout the data generation process to reduce computational cost. By using a greedy search algorithm to optimize the network width schedule, our method achieves performance comparable to baseline diffusion models with significantly reduced computational complexity. Notably, our approach reduces the computational complexity by up to $87.5\%$ without a significant drop in objective metrics, such as perceptual evaluation of speech quality (PESQ) and SI-SDR.

eess.AS↗

arXiv2025

Training Strategies for Modality Dropout Resilient Multi-Modal Target Speaker Extraction

The primary goal of multi-modal TSE (MTSE) is to extract a target speaker from a speech mixture using complementary information from different modalities, such as audio enrolment and visual feeds corresponding to the target speaker. MTSE systems are expected to perform well even when one of the modalities is unavailable. In practice, the systems often suffer from modality dominance, where one of the modalities outweighs the others, thereby limiting robustness. Our study investigates training strategies and the effect of architectural choices, particularly the normalization layers, in yielding a robust MTSE system in both non-causal and causal configurations. In particular, we propose the use of modality dropout training (MDT) as a superior strategy to standard and multi-task training (MTT) strategies. Experiments conducted on two-speaker mixtures from the LRS3 dataset show the MDT strategy to be effective irrespective of the employed normalization layer. In contrast, the models trained with the standard and MTT strategies are susceptible to modality dominance, and their performance depends on the chosen normalization layer. Additionally, we demonstrate that the system trained with MDT strategy is robust to using extracted speech as the enrollment signal, highlighting its potential applicability in scenarios where the target speaker is not enrolled.

eess.AS↗

arXiv2025

Dynamic Slimmable Networks for Efficient Speech Separation

Recent progress in speech separation has been largely driven by advances in deep neural networks, yet their high computational and memory requirements hinder deployment on resource-constrained devices. A significant inefficiency in conventional systems arises from using static network architectures that maintain constant computational complexity across all input segments, regardless of their characteristics. This approach is sub-optimal for simpler segments that do not require intensive processing, such as silence or non-overlapping speech. To address this limitation, we propose a dynamic slimmable network (DSN) for speech separation that adaptively adjusts its computational complexity based on the input signal. The DSN combines a slimmable network, which can operate at different network widths, with a lightweight gating module that dynamically determines the required width by analyzing the local input characteristics. To balance performance and efficiency, we introduce a signal-dependent complexity loss that penalizes unnecessary computation based on segmental reconstruction error. Experiments on clean and noisy two-speaker mixtures from the WSJ0-2mix and WHAM! datasets show that the DSN achieves a better performance-efficiency trade-off than individually trained static networks of different sizes.

eess.AS↗

arXiv2023

New Insights on Target Speaker Extraction

Speaker extraction (SE) aims to segregate the speech of a target speaker from a mixture of interfering speakers with the help of auxiliary information. Several forms of auxiliary information have been employed in single-channel SE, such as a speech snippet enrolled from the target speaker or visual information corresponding to the spoken utterance. The effectiveness of the auxiliary information in SE is typically evaluated by comparing the extraction performance of SE with uninformed speaker separation (SS) methods. Following this evaluation protocol, many SE studies have reported performance improvement compared to SS, attributing this to the auxiliary information. However, such studies have been conducted on a few datasets and have not considered recent deep neural network architectures for SS that have shown impressive separation performance. In this paper, we examine the role of the auxiliary information in SE for different input scenarios and over multiple datasets. Specifically, we compare the performance of two SE systems (audio-based and video-based) with SS using a common framework that utilizes the recently proposed dual-path recurrent neural network as the main learning machine. Experimental evaluation on various datasets demonstrates that the use of auxiliary information in the considered SE systems does not always lead to better extraction performance compared to the uninformed SS system. Furthermore, we offer insights into the behavior of the SE systems when provided with different and distorted auxiliary information given the same mixture input.

eess.AS↗

arXiv2023

Beamformer-Guided Target Speaker Extraction

We propose a Beamformer-guided Target Speaker Extraction (BG-TSE) method to extract a target speaker's voice from a multi-channel recording informed by the direction of arrival of the target. The proposed method employs a front-end beamformer steered towards the target speaker to provide an auxiliary signal to a single-channel TSE system. By allowing for time-varying embeddings in the single-channel TSE block, the proposed method fully exploits the correspondence between the front-end beamformer output and the target speech in the microphone signal. Experimental evaluation on simulated multi-channel 2-speaker mixtures, in both anechoic and reverberant conditions, demonstrates the advantage of the proposed method compared to recent single-channel and multi-channel baselines.

eess.AS↗

arXiv2022

Speaker Verification in Multi-Speaker Environments Using Temporal Feature Fusion

Verifying the identity of a speaker is crucial in modern human-machine interfaces, e.g., to ensure privacy protection or to enable biometric authentication. Classical speaker verification (SV) approaches estimate a fixed-dimensional embedding from a speech utterance that encodes the speaker's voice characteristics. A speaker is verified if his/her voice embedding is sufficiently similar to the embedding of the claimed speaker. However, such approaches assume that only a single speaker exists in the input. The presence of concurrent speakers is likely to have detrimental effects on the performance. To address SV in a multi-speaker environment, we propose an end-to-end deep learning-based SV system that detects whether the target speaker exists within an input or not. First, an embedding is estimated from a reference utterance to represent the target's characteristics. Second, frame-level features are estimated from the input mixture. The reference embedding is then fused frame-wise with the mixture's features to allow distinguishing the target from other speakers on a frame basis. Finally, the fused features are used to predict whether the target speaker is active in the speech segment or not. Experimental evaluation shows that the proposed method outperforms the x-vector in multi-speaker conditions.

eess.AS↗

arXiv2021

Informed Source Extraction With Application to Acoustic Echo Reduction

Informed speaker extraction aims to extract a target speech signal from a mixture of sources given prior knowledge about the desired speaker. Recent deep learning-based methods leverage a speaker discriminative model that maps a reference snippet uttered by the target speaker into a single embedding vector that encapsulates the characteristics of the target speaker. However, such modeling deliberately neglects the time-varying properties of the reference signal. In this work, we assume that a reference signal is available that is temporally correlated with the target signal. To take this correlation into account, we propose a time-varying source discriminative model that captures the temporal dynamics of the reference signal. We also show that existing methods and the proposed method can be generalized to non-speech sources as well. Experimental results demonstrate that the proposed method significantly improves the extraction performance when applied in an acoustic echo reduction scenario.

eess.AS↗

arXiv2021

Noise-Robust Adaptation Control for Supervised Acoustic System Identification Exploiting A Noise Dictionary

We present a noise-robust adaptation control strategy for block-online supervised acoustic system identification by exploiting a noise dictionary. The proposed algorithm takes advantage of the pronounced spectral structure which characterizes many types of interfering noise signals. We model the noisy observations by a linear Gaussian Discrete Fourier Transform-domain state space model whose parameters are estimated by an online generalized Expectation-Maximization algorithm. Unlike all other state-of-the-art approaches we suggest to model the covariance matrix of the observation probability density function by a dictionary model. We propose to learn the noise dictionary from training data, which can be gathered either offline or online whenever the system is not excited, while we infer the activations continuously. The proposed algorithm represents a novel machine-learning based approach to noise-robust adaptation control which allows for faster convergence in applications characterized by high-level and non-stationary interfering noise signals and abrupt system changes.

eess.AS↗