Effect of Singular Value Decomposition Based Processing on Speech Perception

kour, Balvinder; Singh, Randhir; Lehana, Parveen; Rajput, Padmini

doi:10.5121/ijnlc.2013.2102

Cited by 3 publications

(3 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…One of the most important tasks for the blind source extraction is to separate the mixed signals without any information about the original sources and the cocktail parity problem is one of the famous problem solved by BSS [25]- [28]. In the model presented in Figure 3, two separate microphones are used, each of which is a weighted sum of all sources, with the weights based on the distances between the microphones.…”

Section: Proposed Work and Resultsmentioning

confidence: 99%

Cocktail parity problem solution based on modified blind extraction technique

Abdullah

Hamed

Al-Bakry

et al. 2022

IJEECS

View full text Add to dashboard Cite

The Cocktail Party Problem solution is described as being the responsibility of isolating the voice signal in a noisy environment. Two popular methods for resolving this issue are blind source extraction and the Wiener filtering procedure. The blind source extraction approaches like fastICA, JADE and efficient fastICA are useful for extraction data from the mixed signals. The classical optimization techniques such as genetic algorithms or particle swarms for blind source extraction are mostly founded on the gradient and need the objective function, so the using of these techniques is very restricted. In the recent studies, the classical blind source separation techniques will not give the perfect solution for the cocktail parity problem. These methods struggle with convergence speed and accuracy issues as well. In order to enhance the separation process and get over these issues, this work adopted the glowworm swarm technique based on kurtosis as the objective function. The results show that the proposed technique produces good separation. The original and estimated signals are compared for similarity using the cross-correlation function.

show abstract

Section: Proposed Work and Resultsmentioning

confidence: 99%

Cocktail parity problem solution based on modified blind extraction technique

Abdullah

Hamed

Al-Bakry

et al. 2022

IJEECS

View full text Add to dashboard Cite

show abstract

“…The adopted SVD approach, which is basically relying on the generalization of the Eigen decomposition of a positive semi definite normal matrix via an extension of the polar decomposition, is efficient in enhancing the noisy signal by retaining few of the singular values from the decomposition of an over determined, overextended data matrix. An investigation study was performed by Kour et al on the effect of SVD based feature selection of the input speech on the perception of the processed speech signal, where speech of six speakers was recorded and the English language vowels were analyzed using SVD based processing 10 .…”

Section: Related Workmentioning

confidence: 99%

COVID-19 Diagnosis Using Spectral and Statistical Analysis of Cough Recordings Based on the Combination of SVD and DWT

Mohammed¹,

Sultan

Alheeti

et al. 2023

Baghdad Sci.J

View full text Add to dashboard Cite

Healthcare professionals routinely use audio signals, generated by the human body, to help diagnose disease or assess its progression. With new technologies, it is now possible to collect human-generated sounds, such as coughing. Audio-based machine learning technologies can be adopted for automatic analysis of collected data. Valuable and rich information can be obtained from the cough signal and extracting effective characteristics from a finite duration time interval that changes as a function of time. This article presents a proposed approach to the detection and diagnosis of COVID-19 through the processing of cough collected from patients suffering from the most common symptoms of this pandemic. The proposed method is based on adopting a combination of Singular Value Decomposition (SVD), and Discrete Wavelet Transform (DWT). The combination of these two signal processing techniques is gaining lots of interest in the field of speaker and speech recognition. As a cough recognition approach, we found it well-performing, as it generates and utilizes an efficient minimum number of features. Mean and median frequencies, which are known to be the most useful features in the frequency domain, are applied to generate an effective statistical measure to compare the results. The hybrid structure of DWT and SVD, adopted in this approach adds to its efficiency, where a 200 times reduction, in terms of the number of operations, is achieved. Despite the fact that symptoms of the infected and non-infected people used in the study are having lots of similarities, diagnosis results obtained from the application of the proposed approach show high diagnosis rate, which is proved through the matching with relevant PCR tests. The proposed approach is open for more improvements with its performance further assured by enlarging the dataset, while including healthy people.

show abstract

“…The effect of SVD was investigated on speech recognition employing of vowels \a\, \e\, \u\ proposed by Balvinder et al [7]. The effect of reduction in singular value was done and the experimental results show that the number of singular values drastically reduce without significantly affecting the perception of the vowels.…”

Section: Literature Reviewmentioning

confidence: 99%

Real and Complex Wavelet Transform Using Singular Value Decomposition for Malaysian Speaker and Accent Recognition

Abdullah

Vijean

Hariharan

et al. 2020

Lecture Notes in Mechanical Engineering

View full text Add to dashboard Cite

This paper presents a new approach for Malaysian speaker and accent recognition using wavelet feature extraction method, namely Wavelet Packet Transform (WPT), Discrete Wavelet Packet Transform (DWPT) and Dual Tree Complex Wavelet Packet Transform (DT-CWPT). Since Singular Value Decomposition (SVD) was based on factorization and summarization technique which reduces a rectangular matric, it is applied on those features to evaluate the performance for speaker and accent recognition. The features are derived from wavelets and SVD classified with three different classifiers namely k-Nearest Neighbors (k-NN), Support Vector Machine (SVM) and Extreme Learning Machine (ELM). In this work, English digits (0-9) and Malay words database uttered from 75 undergraduate students of Universiti Malaysia Perlis (UniMAP) which are Malays, Chinese and Indian. The Malay words had a combination of consonants and vowels in monosyllable and bi-syllable structure. The accuracy of file-based analysis achieved were above 81% while for frame-based analysis, 93.87% and above were obtained using three different classifiers (k-NN, SVM and ELM) for speaker and accent recognition. Through the experiments, it is observed that accent recognition achieved high recognition rate of 100% for both framed-based analysis and file-based analysis using SVM. The experimental results show the proposed features using SVD achieved high accuracy of 100% using SVM through English digits and Malay words in accent recognition. This indicated that feature extraction using wavelets (WPT, DWPT and DT-CWPT) with SVD can achieve a good performance for both English digits and Malay words.

show abstract

Effect of Singular Value Decomposition Based Processing on Speech Perception

Cited by 3 publications

References 14 publications

Cocktail parity problem solution based on modified blind extraction technique

Cocktail parity problem solution based on modified blind extraction technique

COVID-19 Diagnosis Using Spectral and Statistical Analysis of Cough Recordings Based on the Combination of SVD and DWT

Real and Complex Wavelet Transform Using Singular Value Decomposition for Malaysian Speaker and Accent Recognition

Contact Info

Product

Resources

About