Speaker Identification With Whispered Speech for the Access Control System

Wang, Jia-Ching; Chin, Yu-Hao; Hsieh, Wen-Chi; Lin, Chang-Hong; Chen, Ying-Ren; Siahaan, Ernestasia

doi:10.1109/tase.2015.2467311

Cited by 22 publications

(4 citation statements)

References 34 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…3) Interactivity: Different schools have different management systems [6] , and good human-computer interaction can be modified and adjusted through the terminal installed on the computer [7] to better match the management model of the user. 4) Perfectibility: Through the multi-hierarchy management model, while ensuring that the trapped students are rescued at the first time and safeguarding the property of the library.…”

Section: B Application Of Intelligent University Library Access Contmentioning

confidence: 99%

Design and Application of Intelligent Library Access Control System of University

Sun¹,

Li²

2018

Proceedings of the 2018 International Conference on Education Science and Social Development (ESSD 2018)

View full text Add to dashboard Cite

Traditional university library access control system has its limitation which will cause, which students often get locked in the library by accident. In order to reduce the occurrence of this phenomenon, this article introduces an intelligent university library access control system. We clarify the implementation of the intelligent university library access control system, and use a library control system as an example, by designing a multi-sector system scheduling management application process suitable for the education system. This system has the advantages of intelligence, modularity, interactivity, perfectibility, and generalizability. The system can realize the intelligent upgrade of the university library access control system, responding to the graded incidents such as trapped students and other emergencies, and improve the library service quality and readers' satisfaction.

show abstract

Section: B Application Of Intelligent University Library Access Contmentioning

confidence: 99%

Design and Application of Intelligent Library Access Control System of University

Sun¹,

Li²

2018

Proceedings of the 2018 International Conference on Education Science and Social Development (ESSD 2018)

View full text Add to dashboard Cite

show abstract

“…Jia-Ching, et al [20] proposed a speaker identification system using instantaneous frequencies of the whispered speech signal approximated probability product kernel support vector machine for an access control and compared the performance with pyknogram-based system.…”

Section: International Journal Of Computer Applications (0975 -8887) mentioning

confidence: 99%

Text-independent Speaker Identification in Emotional and Whispered Speech Environments

Jawarkar¹,

Holambe²,

Basu³

2017

IJCA

View full text Add to dashboard Cite

This paper describes challenging task of closed set textindependent speaker identification in emotional and whispered speech environments. In the first phase of the work, speaker identification system is developed using neutral speech and tested using speech samples comprising of six basic emotions of anger, happiness, sadness, disgust, neutral and fear. The performance is analyzed using Mel frequency cepstral coefficients (MFCC), Line spectral frequencies (LSF), and temporal energy of subband cepstral coefficients (TESBCC) feature sets. The second phase of work involves the process of speaker identification system in whispered speech environment. The performance of the speaker identification system degrades drastically for whisper speech utterances. A new feature called temporal Teager energy based subband cepstral coefficients (TTESBCC) is proposed. The comparison of the performance of MFCC, TESBCC, weighted instantaneous frequency (WIF) and TTESBCC feature sets is done for this process. A novel classifiers fusion technique is developed and its performance is compared with that of the individual classifiers. Two databases with speech utterances of thirty nine speakers recorded in the six basic emotions and speech utterances of twenty five speakers in whispered speech are used for experimentation. The speech utterances for database were recorded in Indian languageMarathi. It is observed fusion of classifiers considerably enhances the speaker identification accuracy in both emotional and whispered speech environments.

show abstract

“…Because of these characteristics, whispered speech is widely used in places where loud noises are prohibited such as conference rooms, libraries, and concert halls. Because of its potential applications [3][4][5][6], in recent years, studies on whispered speech (e.g., whispered speech emotion recognition, whispered speech enhancement, whispered speech recognition, and whispered speech conversion) have gradually attracted researchers' attention. Among them, whispered speech conversion, a technique that converts whispered speech to normal speech, has been widely used in mobile communication, medical equipment, security monitoring, and crime identification [7][8][9].…”

Section: Introductionmentioning

confidence: 99%

Whispered Speech Conversion Based on the Inversion of Mel Frequency Cepstral Coefficient Features

et al. 2022

View full text Add to dashboard Cite

A conversion method based on the inversion of Mel frequency cepstral coefficient (MFCC) features was proposed to convert whispered speech into normal speech. First, the MFCC features of whispered speech and normal speech were extracted and a matching relation between the MFCC feature parameters of whispered speech and normal speech was developed through the Gaussian mixture model (GMM). Then, the MFCC feature parameters of normal speech corresponding to whispered speech were obtained based on the GMM and, finally, whispered speech was converted into normal speech through the inversion of MFCC features. The experimental results showed that the cepstral distortion (CD) of the normal speech converted by the proposed method was 21% less than that of the normal speech converted by the linear predictive coefficient (LPC) features, the mean opinion score (MOS) was 3.56, and a satisfactory outcome in both intelligibility and sound quality was achieved.

show abstract

Speaker Identification With Whispered Speech for the Access Control System

Cited by 22 publications

References 34 publications

Design and Application of Intelligent Library Access Control System of University

Design and Application of Intelligent Library Access Control System of University

Text-independent Speaker Identification in Emotional and Whispered Speech Environments

Whispered Speech Conversion Based on the Inversion of Mel Frequency Cepstral Coefficient Features

Contact Info

Product

Resources

About