Results 51 to 60 of about 167,964,167 (121)

Transfer Learning Algorithm for Enhancing the Unlabeled Speech

IEEE Access, 2020
To improve the generalization ability of speech enhancement algorithms for unlabeled noisy speech, a speech enhancement transfer learning model based on the feature-attention multi-kernel maximum mean discrepancy (FA-MK-MMD) is proposed.
Ruiyu Liang, Zhenlin Liang, Jiaming Cheng, Yue Xie, Qingyun Wang   +4 more
doaj   +1 more source

CITISEN: A Deep Learning-Based Speech Signal-Processing Mobile Application

IEEE Access, 2022
This study presents a deep learning-based speech signal-processing mobile application known as CITISEN. The CITISEN can perform three functions: speech enhancement (SE), model adaptation (MA), and background noise conversion (BNC), which allow CITISEN to
Yu-Wen Chen, Kuo-Hsuan Hung, You-Jin Li, Alexander Chao-Fu Kang, Ya-Hsin Lai, Kai-Chun Liu, Szu-Wei Fu, Syu-Siang Wang, Yu Tsao   +8 more
doaj   +1 more source

A neural coding method based on feature sensing

IET Communications, Volume 19, Issue 1, January/December 2025.
It has been shown that human neural coding is characterized by non‐linearity and that different neurons are more responsive to stimuli with specific features. Based on this, we propose a neural coding method based on feature sensing (feature sensing neural coding; FSNC). Taking speech signals as an example to simulate the process of auditory formation,
Dongbin He, Aiqun Hu, Kaiwen Sheng
wiley   +1 more source

DeCGAN: Speech Enhancement Algorithm for Air Traffic Control

Algorithms
Air traffic control (ATC) communication is susceptible to speech noise interference, which undermines the quality of civil aviation speech. To resolve this problem, we propose a speech enhancement model, termed DeCGAN, based on the DeConformer generative
Haijun Liang, Yimin He, Hanwen Chang, Jianguo Kong   +3 more
doaj   +1 more source

Speech Compressive Sampling Using Approximate Message Passing and a Markov Chain Prior

Sensors, 2020
By means of compressive sampling (CS), a sparse signal can be efficiently recovered from its far fewer samples than that required by the Nyquist–Shannon sampling theorem.
Xiaoli Jia, Peilin Liu, Sumxin Jiang
doaj   +1 more source

Distributed MVDR Beamformer Based on Distributed Steering Vector Estimation in Acoustic Sensor Network

Electronics Letters, Volume 61, Issue 1, January/December 2025.
This article proposes a distributed minimum variance distortionless response (MVDR) beamformer for speech enhancement, where the network‐wide steering vector used for generating MVDR is estimated in a distributed way. This method is iteratively performed, and in each iteration, the steering matrix and the beamformer coefficient are simultaneously ...
Xingyue Cui, Rui Wang
wiley   +1 more source

Speech Enhancement Based on Dual-Path Cross-Parallel Conformer Network

IEEE Access
The speech quality can be reduced by long-term and short-term noise, and frequency-domain single-path speech enhancement methods suffer from phase missing.
Qing Zhao, Ying Gao, Zhuoran Cai, Shifeng Ou   +3 more
doaj   +1 more source

Brain‐Controlled Augmented Hearing for Spatially Moving Conversations in Multi‐Talker Environments

Advanced Science, Volume 11, Issue 41, November 6, 2024.
This paper presents a novel brain‐controlled binaural hearing device algorithm, evaluated with a realistic experimental paradigm. The method integrates binaural speech separation with auditory attention decoding to enhance the attended conversation, demonstrating substantial improvement in speech intelligibility and reduction in listening effort in ...
Vishal Choudhari, Cong Han, Stephan Bickel, Ashesh D. Mehta, Catherine Schevon, Guy M. McKhann, Nima Mesgarani   +6 more
wiley   +1 more source

Noise Reduction from Speech Signal based on Wavelet Transform and Kullback-Leibler Divergence

International Journal of Information and Communication Technology Research, 2009
A new method for speech enhancement based on Kullback-Leibler (K-L) divergence has been presented in this paper. First, the algorithm performs wavelet-packet transform to noisy speech and decomposes it into sub-bands; then we apply a threshold on ...
Shima Tabibian, Ahmad Akbari
doaj  

Single-Channel Speech Enhancement Algorithm Based on ME-MGCRN in Low Signal-to-Noise Scenario

IEEE Access
In low signal-to-noise ratio (SNR) conditions, to address the problem of poor speech enhancement effect of traditional neural networks, this paper combines Convolution Recurrent Neural Network (CRN) with Gated Linear Units (GLU) to extract speech ...
Chaofeng Lan, Shilong Zhao, Huan Chen, Lei Zhang, Yuchen Yang, Zixu Fan, Meng Zhang   +6 more
doaj   +1 more source