DeepVQE: Real time deep voice quality enhancement for joint acoustic echo cancellation, noise suppression and dereverberation

E Indenbom, NC Ristea, A Saabas, T Parnamaa… - arXiv preprint arXiv …, 2023 - arxiv.org
Acoustic echo cancellation (AEC), noise suppression (NS) and dereverberation (DR) are an
integral part of modern full-duplex communication systems. As the demand for …

Cross-attention mechanism-based spectrum sensing in generalized Gaussian noise

H Xi, W Guo, Y Yang, R Yuan, H Ma - Scientific Reports, 2024 - nature.com
Spectrum sensing (SS) technology is essential for cognitive radio (CR) networks to
effectively identify and utilize idle spectrum resources. Due to the influence of noise …

Dual-Branch Guidance Encoder for Robust Acoustic Echo Suppression

H Han, X Peng, D Kim, Y Lu… - IEEE/ACM Transactions …, 2024 - ieeexplore.ieee.org
For efficient real-time speech communication, it is crucial to design a robust acoustic echo
cancellation (AEC) system that can effectively mitigate echo signals, which degrade speech …

A Novel Feature-Fusion-Based Sparse Masked Attention Network for Acoustic Echo Cancellation Using Wavelet and STFT Synergies

VS Ishwarya, M Kothandaraman - Circuits, Systems, and Signal …, 2024 - Springer
Deep learning-based acoustic echo cancellation (AEC) systems have advanced
significantly, yet previous methods often rely on a single transform, such as short-time fourier …

Efficient High-Performance Bark-Scale Neural Network for Residual Echo and Noise Suppression

E Seidel, P Mowlaee… - ICASSP 2024-2024 IEEE …, 2024 - ieeexplore.ieee.org
In recent years, the introduction of neural networks (NNs) into the field of speech
enhancement has brought significant improvements. However, many of the proposed …

Syncnet: Correlating objective for time delay estimation in audio signals

A Raina, V Arora - … 2023-2023 IEEE International Conference on …, 2023 - ieeexplore.ieee.org
This study addresses the task of performing robust and reliable time-delay estimation in
signals in noisy and reverberating environments. In contrast to the popular signal processing …

[PDF][PDF] MSA-DPCRN: A Multi-Scale Asymmetric Dual-Path Convolution Recurrent Network with Attentional Feature Fusion for Acoustic Echo Cancellation

Y Ni, C Pang, C Huang, C Zou - Proc. Interspeech 2024, 2024 - isca-archive.org
Echo cancellation plays a crucial role in modern speech applications. Numerous deep-
learning models have been developed for the echo cancellation task and achieved great …

FADI-AEC: Fast Score Based Diffusion Model Guided by Far-end Signal for Acoustic Echo Cancellation

Y Liu, L Wan, Y Li, Y Huang, M Sun, J Luan… - arXiv preprint arXiv …, 2024 - arxiv.org
Despite the potential of diffusion models in speech enhancement, their deployment in
Acoustic Echo Cancellation (AEC) has been restricted. In this paper, we propose DI-AEC …

FSD: Acoustic Echo Cancellation with Fewer Step Diffusion

Y Liu, L Wan, Y Huang, M Sun, C Zhao, Z Ni… - … NeurIPS 2024 Workshop … - openreview.net
Despite the promising capabilities of diffusion models in speech enhancement, their
application in Acoustic Echo Cancellation (AEC) has been limited. In this paper, we …