An overview of speech recognition system based on the support vector machines

Sonkamble, Balwant A.; Doye, Dharmpal D.

doi:10.1109/iccce.2008.4580709

Cited by 17 publications

(7 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…In the case of SVM, unique input space is mapped onto a greater dimensional feature space, where an optimal isolating hyperplane to enlarge margin amongst two classes, ie, it enlarges the system's generalization capability. When developing SVM classifiers, take the following assumptions into consideration 29 To select input speech samples autonomously; The dimensions of input speech samples are equivalent; Kernel integrates all the earlier knowledge on the speech data.…”

Section: Proposed Methodologymentioning

confidence: 99%

See 1 more Smart Citation

Enhanced polynomial kernel (EPK)–based support vector machine (SVM) (EPK‐SVM) classification technique for speech recognition in hearing‐impaired listeners

Pavithra

Janakiraman

2019

Concurrency and Computation

View full text Add to dashboard Cite

Summary Automatic speech recognition of Tamil Language with Hearing‐Impaired becomes difficult task in recent decades. In order to deal with the challenges with speech perception in hostile listening situations, Noise Reduction (NR) algorithms have been developed with the aim of improving the speech intelligibility (SI), speech quality, and ease of listening. Even though the noises are removed, extraction of correct features from the speech becomes difficult task. The major aim of this work is to introduce a Classification Technique for Speech Recognition in Hearing‐Impaired Listeners. The binary mask along with its binary weights and the Wiener filter with constant weights form the representatives of a hard and a soft‐decision scheme for time‐frequency masking. In the proposed Log Frequency Power Coefficients (LFPC), Pitch, Mel‐Frequency Cepstral Coefficients (MFCCs), Energy, formants, and intensity as input feature vectors are extracted from preprocessed signals. Then, for automatic speech recognition process, Enhanced Polynomial Kernel (EPK)–based Support Vector Machine (SVM) (EPK‐SVM) classifier is proposed for Hearing Impaired in Tamil language is implemented in MATLAB software. The results obtained showed that SVM is found to be potential in hearing‐impaired application and is validated via the use of the recognition accuracy and error rate.

show abstract

Section: Proposed Methodologymentioning

confidence: 99%

“…In addition the proposed work, “p → positive integer (0‐1)” is added, which is computed based on the feature vector. If the features become more significance, the values are assigned to 0.5 to 1; else, the value is assigned to 0.1‐0.5 29

italicEPK = K bold= ((), K_{1} . K_{2}) p .

…”

Section: Proposed Methodologymentioning

confidence: 99%

Enhanced polynomial kernel (EPK)–based support vector machine (SVM) (EPK‐SVM) classification technique for speech recognition in hearing‐impaired listeners

Pavithra

Janakiraman

2019

Concurrency and Computation

View full text Add to dashboard Cite

show abstract

“…All biometric devices take a number of measurements from an individual then digitally process the result of these measurements and save this representation of the individual's traits into a template. Templates are then stored in a database associated with the device or in a smartcard given to the individual [1].…”

Section: Introductionmentioning

confidence: 99%

The Use of Biometric Technology for Effective Personnel Management System in Organization

Unal¹,

Tecim²

2018

KSS

View full text Add to dashboard Cite

Although the concept of attendance systems has been carried over the years, in recent times the forms of its application has changed. Companies being aware of the importance of personnel attendance to overcome the problems raised from manual attendance systems have started to take advantage of biometric systems. Particularly, fingerprint and facial recognition are the two most used forms for biometric identification, since it is considered as the most reliable and secure method in terms of its uniqueness. Because manual attendance systems are timeconsuming and ineffective, companies review their control mechanisms for personnel attendance to integrate new technologies in their operations. This article proposes a new generation technological structure used to get effective results in personnel attendance systems. There are plenty of personnel attendance control systems in the market both for multinational companies or small companies. However, the number of web-based form of these systems is limited. Web-based personnel attendance control systems is quickly becoming one of the fastest growing technologies that enables instant data flow and reporting. According to the literature reviewed, more and more companies in Turkey have benefited over the time from web-based personnel attendance control systems. Nevertheless, there are not enough researches about it. The aim of this article is to design and implement a web-based attendance system for personnel in an organization by using biometric system (fingerprints and facial recognition combining with RFID card and password authentication) and support managers to make effective and efficient decision-making process. The proposed system has been implemented by following the steps of Software Development Life Cycle (SDLC). In the process of software development, a waterfall model was chosen that was used in many software projects and that composed of analysis, design, coding, test, version and maintenance phases. Since it is a linear sequential, progress is seen as flowing steadily downward (like a waterfall) through the phases of software implementation. Even though the waterfall approach is the earliest approach, it is still most widely known for software development. This research is expected to help managers in educational institutions in terms of effective personnel management, especially for institutions that have large number of employees. In addition, the developed system can also help educational institutions for adopting their personnel attendance system to new technologies. It was also known that private organizations use this kind of systems. However, educational institutions can also take advantage of biometric data in the web-based personnel management system. Keywords: personnel attendance control system, personnel management, biometric systems, fingerprints and facial recognition

show abstract

“…In (Bresolin, 2008) SVM is used for classifying Brazilian Portuguese spoken digits with polynomial kernel function. Several studies in speech recognition are based on combination of SVM and HMM for modelling the speech signals (Ganapathiraju, 2004) and (Sonkamble, 2008). Another approach that is used for improving both the generality and learning ability in SVM classifier for speech recognition is the convex combination of polynomial and Gaussian kernels (Bai, 2008).…”

Section: Introductionmentioning

confidence: 99%

Support Vector Data Description for Spoken Digit Recognition

Tavanaei¹,

Ghasemi²,

Tavanaei³

et al. 2012

Proceedings of the International Conference on Bio-Inspired Systems and Signal Processing

View full text Add to dashboard Cite

A classifier based on Support Vector Data Description (SVDD) is proposed for spoken digit recognition. We use the Mel Frequency Discrete Wavelet Coefficients (MFDWC) and the Mel Frequency cepstral Coefficients (MFCC) as the feature vectors. The proposed classifier is compared to the HMM and results are promising and we show the HMM and SVDD classifiers have equal accuracy rates. The performance of the proposed features and SVDD classifier with several kernel functions are evaluated and compared in clean and noisy speech. Because of multi resolution and localization of the Wavelet Transform (WT) and using SVDD, experiments on the spoken digit recognition systems based on MFDWC features and SVDD with weighted polynomial kernel function give better results than the other methods.

show abstract

An overview of speech recognition system based on the support vector machines

Cited by 17 publications

References 11 publications

Enhanced polynomial kernel (EPK)–based support vector machine (SVM) (EPK‐SVM) classification technique for speech recognition in hearing‐impaired listeners

Enhanced polynomial kernel (EPK)–based support vector machine (SVM) (EPK‐SVM) classification technique for speech recognition in hearing‐impaired listeners

The Use of Biometric Technology for Effective Personnel Management System in Organization

Support Vector Data Description for Spoken Digit Recognition

Contact Info

Product

Resources

About