Automatic short utterance speaker recognition using stationary wavelet coefficients of pitch synchronised LP residual

Sreehari, V. R.; Mary, Leena

doi:10.1007/s10772-021-09895-z

Cited by 3 publications

(3 citation statements)

References 44 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…As the discrete wavelet decomposition process is down sampling to obtain scale coefficients and wavelet coefficients, it is easy to lead to time-varying translation and difficult to retain the continuity of the original signal. Stationary wavelet transform(SWT) removes the down-sampling [28,29]. So, after SWT decomposition, the length of each level wavelet coefficients is same with the length of the original signal, and it has important translation invariance.…”

Section: Stationary Wavelet Transformmentioning

confidence: 99%

Partial discharge de-noising based on hybrid particle swarm optimization SWT adaptive threshold

Fang

2024

IEEE Access

View full text Add to dashboard Cite

A hybrid particle swarm optimization stationary wavelet adaptive threshold denoising (HPO-SWT-ATD) method was proposed to improve the adaptive ability of wavelet transform in partial discharge signal denoising. In the proposed method, the partial discharge signal is decomposed by stationary wavelet transform(SWT) and the multiorder differentiable function based on the Stein unbiased likelihood estimate (SURE) is used as the denoising threshold function. In threshold selection, the improved particle swarm optimization algorithm is used for global adaptive search to select the optimal denoising threshold. The denoising experiments are carried out on the simulated partial discharge signals and the measured partial discharge signals.The experiment results show that, compared with the hard threshold method, particle swarm optimization threshold method, genetic algorithm optimization threshold method, Wiener filter method and modal decomposition method, the proposed method can better remove the white noise in the PD signal, and the denoising signal distortion degree is smaller.

show abstract

Section: Stationary Wavelet Transformmentioning

confidence: 99%

Partial discharge de-noising based on hybrid particle swarm optimization SWT adaptive threshold

Fang

2024

IEEE Access

View full text Add to dashboard Cite

show abstract

“…As a corollary, a slew of open-source implementations [7,11] are actively being incorporated. TensorFlow [37], PyTorch [38], ASVtorch [39], Alize [40], Kaldi [16] and HTK [41] are a few of the most prominent options. Using these toolkits will benefit DL research and production because they allow for flexible model creation at a big scale and in varied situations.…”

Section: Ubm-gmmmentioning

confidence: 99%

“…Alize [16] JAVA Includes all functions required to use Gaussian mixtures. ASVtorch [39] Python Use PyTorch machine learning approach. Keras [3] Python Lightweight, user-friendly and simple in design.…”

Section: Pythonmentioning

confidence: 99%

Analysis of Human Voice for Speaker Recognition: Concepts and Advancement

Sumit Srivastava

2024

jes

View full text Add to dashboard Cite

Human voice or speech is a contactless, non-invasive biometric trait for human recognition, easy to use with minimal computer complexity and inexpensive to implement. Speaker recognition (SR) has turned out to be a magnificent approach using speech as the central premise since decades. Its broad range of usages, like forensic speech verification to identify culprits by law enforcement authorities and access control to mobile banking, mobile shopping, etc., has made it a lucrative area of research. Also, the ease of use and dependability of SR will significantly assist people with disabilities in securely accessing and reaping the benefits of digital-era services. Additionally, the emergence of numerous deep learning methods for feature extraction and classification, has helped SR to achieve tremendous progress. This paper presents a comprehensive study on the progression of SR for decades till the present, including integration with Blockchain and challenges. It covers most of the factors that influence SR performance such as fundamentals and structure of SR, different speech pre-processing techniques, various speech features, feature extraction techniques, traditional and neural network-based classification techniques and deep learning-based SR toolkits. As a consequence, in this digital Blockchain era, it will help to design robust and reliable recognition-based services for mankind.

show abstract

Stationary wavelet Filtering Cepstral coefficients (SWFCC) for robust speaker identification

Missaoui,

Lachiri

2025

Applied Acoustics

View full text Add to dashboard Cite

Automatic short utterance speaker recognition using stationary wavelet coefficients of pitch synchronised LP residual

Cited by 3 publications

References 44 publications

Partial discharge de-noising based on hybrid particle swarm optimization SWT adaptive threshold

Partial discharge de-noising based on hybrid particle swarm optimization SWT adaptive threshold

Analysis of Human Voice for Speaker Recognition: Concepts and Advancement

Stationary wavelet Filtering Cepstral coefficients (SWFCC) for robust speaker identification

Contact Info

Product

Resources

About