A voice activity detection algorithm using deep learning in time–frequency domain

S Mavaddati - Neural Computing and Applications, 2024 - Springer
Voice activity detection (VAD) is an important component of signal processing that is critical
for various applications, including speech recognition, speaker recognition, and speaker …

Speech enhancement using sparse dictionary learning in wavelet packet transform domain

S Mavaddaty, SM Ahadi, S Seyedin - Computer Speech & Language, 2017 - Elsevier
Sparse coding, as a successful representation method for many signals, has been recently
employed in speech enhancement. This paper presents a new learning-based speech …

A novel chicken voice recognition method using the orthogonal matching pursuit algorithm

B Cheng, S Zhong - 2015 8th International Congress on Image …, 2015 - ieeexplore.ieee.org
In an ecological breeding environment, feeders usually don't know whether their chicken are
in good condition. Fortunately, Chicken voices reveal a lot of messages and it is easy to …

A novel adaptive algorithm for estimation of sparse parameters in non-Gaussian noise

M Hajiabadi, B Razeghi, M Mir - 2015 International Conference …, 2015 - ieeexplore.ieee.org
The goal of this paper is to propose a novel diffusion adaptive algorithm for estimation of
sparse system with non-Gaussian noise. The proposed adaptive algorithm uses zero-norm …

Speech endpoint detection in fixed differential beamforming combined with modulation domain

H Wang, Q Zeng, X Zhao - Journal of Physics: Conference Series, 2021 - iopscience.iop.org
The actual speech signal is always in a complex environment, which affects the accuracy of
speech endpoint detection. In order to improve the accuracy of speech endpoint detection …

[PDF][PDF] A Voice Activity Detection Algorithm Using Sparse Non-negative Matrix Factorization-based Model Learning in Spectro-Temporal Domain

S Mavaddati - International Journal of Engineering, 2023 - ije.ir
Voice activity detectors are presented to extract silence/speech segments of the speech
signal to eliminate different background noise signals. A novel voice activity detector is …

Multimodal weighted dictionary learning

A Taalimi, H Shams, A Rahimpour… - 2016 13th IEEE …, 2016 - ieeexplore.ieee.org
Classical dictionary learning algorithms that rely on a single source of information have
been successfully used for the discriminative tasks. However, exploiting multiple sources …

Stages of Development of Speech Signal Processing, Problems and Algorithms

BU Abdumurodovich, AT Narzullayevich… - The Journal of …, 2024 - journal.ciees.eu
This article develops mathematical methods of learning and decision-making in speech
recognition, when extracting informative properties from speech signals, intelligent …

A Cross Dataset Approach for Noisy Speech Identification

AK Punnoose - International Conference on Machine Intelligence and …, 2022 - Springer
This paper presents an approach for identifying noisy speech recording using a multi-layer
perceptron (MLP) trained to predict phoneme from acoustic features. Characteristics of MLP …

A Cross Dataset Approach for Noisy Speech Identification Check for updates

AK Punnoose - … Techniques for Data Engineering: Proceedings of …, 2023 - books.google.com
Noisy speech poses a great challenge to a real-time, real-world speech recognition system.
Speech recognition errors can be introduced at the phoneme level or at the word level …