Feature Data Reduction of MFCC Using PCA and SVD in Speech Recognition System

Winursito, Anggun; Hidayat, Risanuri; Bejo, Agus; Utomo, Muhammad Nur Yasir

doi:10.1109/icscee.2018.8538414

Cited by 25 publications

(14 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Kazuya's research utilizes the Internet network in general and uses Google Hangout tools as a video conference media. The results of the experiments conducted found that respondents had difficulty in following the learning process because of the limited audio and video quality [13]. This problem occurs because the remote class that is carried out still gathers students in one physical class and learns through one screen and speakers [12].…”

Section: Introductionmentioning

confidence: 99%

Tools and Strategy for Distance Learning to Respond COVID-19 Pandemic in Indonesia

Utomo¹,

Sudaryanto²,

Saddhono³

2020

ISI

View full text Add to dashboard Cite

Distance learning is a learning process that allows students and instructors are in different physical locations. During the COVID-19 pandemic, various countries including Indonesia chose the distance learning option to avoid the spread of the pandemic. However, the implementation of distance learning is not without problems. In Indonesia, the problems to implement distance learning are enormous both in terms of equitable distribution of infrastructure and costs for accessing the internet. To overcome these problems, research about best distance learning tools and its implementation strategy is really needed. Therefore, this research aimed to analyze the strategies and tools for implementing distance learning that reliable and cost-effective for the student at the same time. Based on research that has been conducted by analyzing questionnaire surveys of 256 students in Indonesia, this research recommends tools combination strategy consists of Google Classroom tool as a learning app, Whatsapp group as broadcast messaging and Zoom as a video conference media for distance learning. This research also recommended to maximize the elearning/learning app features for theoretical lessons and consider video conference just in practical lessons so that the distance learning costs become cheaper for students.

show abstract

Section: Introductionmentioning

confidence: 99%

Tools and Strategy for Distance Learning to Respond COVID-19 Pandemic in Indonesia

Utomo¹,

Sudaryanto²,

Saddhono³

2020

ISI

View full text Add to dashboard Cite

show abstract

“…One of the latest feature extraction method developments is MFCC + PCA. Several studies have been carried out by combining the MFCC and PCA methods and producing good performance [18], [23], [24]. Wavelet-based denoising methods are also often added as anti-noise in several studies [17], [25].…”

Section: Proposed Methodsmentioning

confidence: 99%

“…The analysis was conducted at one of the MFCC stages, the Fast Fourier Transform (FFT) stage. One of the MFCC stages is FFT serves to change signal from a time domain into a frequency domain [18]. Speech signal data changed in the frequency domain in the FTT process shows the part of data that as affected and not affected by the noise.…”

Section: Introductionmentioning

confidence: 99%

A Modified MFCC for Improved Wavelet-Based Denoising on Robust Speech Recognition

Hidayat¹,

Winursito²

2021

IJIES

Self Cite

View full text Add to dashboard Cite

Research on the current speech recognition system leads to the creation of a noise-resistant system. The Mel Frequency Cepstral Coefficients (MFCC) extraction method becomes a popular method in the speech recognition system. In this paper, the MFCC's weakness of noise interference is the main reason underlies the accomplishment of a robust speech recognition system. Development was carried out by improving the denoising performance using a wavelet transform. Modifications were carried out by analyzing the weakness of the wavelet denoising process on the recognition system using the MFCC method. The analysis was conducted at one of the MFCC stages, the Fast Fourier Transform (FFT) stage. The proposed method was conducted by performing the denoising process using Wavelet only on the noise-related data based on the FFT process' analysis results. The study utilized speech data in the form of eleven isolated words in English added with noise with several different characteristics. Results showed that the proposed method was capable of generating a better accuracy than conventional wavelet denoising methods on the signal to noise ratio (SNR) of 10dB, 15dB, and 20dB using a Fejer Korovkin 6 wavelet type. The highest accuracy increase of the proposed method was in signal to noise ratio (SNR) of 15dB with a rise of 4.63%, followed by a 3.96% increase at 20dB intensity, and 2.3% at 10dB intensity. The performance of the proposed method is then compared with other methods. The results show that the proposed method has the best performance on clean speech and noisy speech at SNR intensities of 10dB, 15dB, and 20dB.

show abstract

“…Anggun et al [10] researched on feature reduction data of MFCC using Principal Component Analysis (PCA) and SVD in speech recognition system. The data reduction process is designed in two version and classified using SVM classifier.…”

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

Feature Data Reduction of MFCC Using PCA and SVD in Speech Recognition System

Cited by 25 publications

References 10 publications

Tools and Strategy for Distance Learning to Respond COVID-19 Pandemic in Indonesia

Tools and Strategy for Distance Learning to Respond COVID-19 Pandemic in Indonesia

A Modified MFCC for Improved Wavelet-Based Denoising on Robust Speech Recognition

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

Contact Info

Product

Resources

About