• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.10 no.7
• /
• pp.1307-1311
• /
• 2006

In this paper, we propose new speech feature parameter using the Matrix Factorization for appearance part-based features of speech spectrum. The proposed parameter represents effective dimensional reduced data from multi-dimensional feature data through matrix factorization procedure under all of the matrix elements are the non-negative constraint. Reduced feature data presents p art-based features of input data. We verify about usefulness of NMF(Non-Negative Matrix Factorization) algorithm for speech feature extraction applying feature parameter that is got using NMF in Mel-scaled filter bank output. According to recognition experiment results, we confirm that proposed feature parameter is superior to MFCC(Mel-Frequency Cepstral Coefficient) in recognition performance that is used generally.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.9 no.2
• /
• pp.73-80
• /
• 2009

Although it is relatively difficult to eavesdrop the commonly used PSTN in that it is connected with direct circuit, it is difficult to ensure the secret of call on Internet because many users can connect to the Internet at the same time. However, it is needed to ensure secret of voice call in a special situation. Due to the fact that many users can connect to the internet at the same time, VoIP can always be in a defenseless state by hackers. Therefore, in this paper, we have developed the increased voice security internet telephone terminal and measured conversation quality by adopting VPN PPTP based on SIP and using tunnel method in transmitting voice data to prevent eavesdrop of internet telephone.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.10 no.6
• /
• pp.63-69
• /
• 2010

Today, Internet Telephony Services based on VoIP are gaining tremendous popularity for general user. Therefore a various demands of the user keep up increase, the most important requirements of these is voice security about telephony system. It is needed to ensure secret of voice call in a special situation. Due to the fact that many users can connect to the internet at the same time, VoIP can always be in a defenseless state by hackers. Therefore, in this paper, we have developed VPN IP-PBX for the voice security and measured conversation quality by adopting VPN IPsec based on SIP and using tunnel method in transmitting voice data to prevent eavesdrop of voice data. This VPN IP-PBX that is connected Soft-phone provide various optional services.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.7 no.3
• /
• pp.475-483
• /
• 2012

The characteristic features of speech signal do not vary significantly from frame to frame. Therefore, it is advisable to reduce the redundancy involved in the similar feature vectors. The objective of this paper is to search for the optimal condition of minimum redundancy and maximum relevancy of the speech feature vectors in speech recognition. For this purpose, we realize redundancy reduction by way of a vigilance parameter and investigate the resultant effect on the speaker-independent speech recognition of isolated words by using FVQ/HMM. Experimental results showed that the number of feature vectors might be reduced by 30% without deteriorating the speech recognition accuracy.

• Phonetics and Speech Sciences
• /
• v.4 no.2
• /
• pp.105-114
• /
• 2012

This paper will discuss the difference between self assessment of voice disorders and the hearer voice assessment of a comparative group of normal subjects. The study was conducted on 25 voice disorder subjects and 32 hearers of a comparative group of normal subjects. The results are as follows. Firstly, in K-VHI and VHI-H, the hearers of the comparative group of normal subjects perceived more serious voice disorders than the voice disorder group in all sub-domains. Likewise, in K-VQOL and VRQOL-H, the hearers of the comparative group of normal subjects perceived more serious voice disorders than the voice disorder group in all sub-domains. Secondly, the hearer voice assessment of the comparative group of normal subjects showed no difference in gender regarding the perception of the severity of voice disorder issues. Thirdly, the hearer voice assessment of the comparative group of normal subjects states that in the emotional aspects of VHI-H, professional voice users perceive more serious voice disorders than others. Accordingly, in VRQOL-H, there was no difference in use of the voice between professionals and others.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2016.05a
• /
• pp.293-296
• /
• 2016

Speech Signals consist of signals of consonants and vowels, but the lasting time of vowels is much longer than that of consonants. It can be assumed that the correlations between signal blocks in speech signal is very high. But the correlations between signal blocks in various frequency bands can be quite different. Each speech signal is divided into blocks which have 128 speech data. FFT is applied to each block. Various frequency areas of the results of FFT are taken and Covariance matrix between blocks in a speech signal is extracted and finally eigenvalues of those matrix are obtained. It is studied that in the eigenvalues of various frequency bands which band can be used to get more reliable result.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2016.05a
• /
• pp.457-459
• /
• 2016

This lecture support system can be used to smoothly transfer the sound in the auditorium or the particular outdoor space. Commercial lecture support system is useful but very expensive. Therefore in this paper we have designed and developed lecture support system using a mobile phone. We can exactly hear the lecture in difficult situation using this system. The system provides the ability to save a lecture in the storage, so we can hear the lecture repeatedly.

• Proceedings of the Acoustical Society of Korea Conference
• /
• spring
• /
• pp.91-94
• /
• 2002

음성인식 시스템의 실용화를 위해서 우선적으로 해결되어야 될 문제중 하나로 잡음환경하에서의 끝점검출을 들 수 있다. 잡음이 존재하지 않는 환경에서는 기존의 에너지 파라미터만으로도 어느정도 신뢰성있는 끝점 구간을 검출할 수 있으나 도심 소음과 같은 실제 잡음환경하에서는 대부분 좋지 않은 결과를 보인다. 본 논문에서는 도심환경의 배경잡음을 제거하는 방법으로 입력되는 음성에 대하여 주변소음에 의해 손상된 음성스펙트럼의 크기 성분만을 제거하는 전처리 기법인 Bark scale에 기반한 스펙트럼 차감법을 사용하고, 인간의 청각특성을 고려하여 음성의 주파수 대역을 3개의 대역으로 분리한 후, 대역별로 세밀한 에너지 문턱치값을 설정하여 음성의 끝점을 탐색하는 방법을 제안한다. 제안한 방법의 유효성을 확인하기 위해 실제 사무실 및 지하철역 등의 잡음환경하에서 녹음된 데이터베이스를 이용하여 끝점검출을 수행한 결과 기존의 에너지와 영교차율을 이용한 방법에 비해 평균 $46\%$의 오차율 감소와 대역에너지만을 사용한 경우에 비해 평균 $17\%$의 오차율 감소를 나타내어 제안한 방법의 유효성을 확인할 수 있었다.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.8 no.2
• /
• pp.359-364
• /
• 2004

In this paper, we implemented real-time speaker undependent speech recognizer that is robust in noise environment using DSP(Digital Signal Processor). Implemented system is composed of TMS320C32 that is floating-point DSP of Texas Instrument Inc. and CODEC for real-time speech input. Speech feature parameter of the speech recognizer used robust feature parameter in noise environment that is transformed feature space of MFCC(met frequency cepstral coefficient) using ICA(Independent Component Analysis) on behalf of MFCC. In recognition result in noise environment, we hew that recognition performance of ICA feature parameter is superior than that of MFCC.

• Proceedings of the Acoustical Society of Korea Conference
• /
• autumn
• /
• pp.53-56
• /
• 2001

사람은 연령, 성별 등에 따라 성도(vocal tract), 성대(vocal cord, 혹은 vocal fold), 비강(nasal tract)등 발성기관의 차이가 있고, 이는 음성의 음색, 높낮이 등 음향 특성에 영향을 미치며, 시간이 지나감에 따라 변하는 특성을 가지고 있다. 예를 들어, 발성기관의 차이가 큰 남성과 여성은 동일한 단어를 발성하더라도 음향학적으로 매우 큰 차이를 보이며, 이러한 특성은 다른 문장 발성 시에도 음향학적으로 일정한 영향을 미치게 되므로 정적특성이라 한다. 본 논문에서는 이러한 정적특성 중 음성의 발성크기에 따른 Glottal Spectrum을 비교 $\cdot$분석 하고자 한다.