• Journal of information and communication convergence engineering
• /
• v.1 no.4
• /
• pp.205-208
• /
• 2003

Voice activity detection is a important problem in the speech recognition and speech communication. This paper introduces new feature parameter which are reconstructed by spectral entropy of information theory for robust voice activity detection in the noise environment, then analyzes and compares it with energy method of voice activity detection and performance. In experiments, we confirmed that spectral entropy and its reconstructed parameter are superior than the energy method for robust voice activity detection in the various noise environment.

• The Journal of the Acoustical Society of Korea
• /
• v.28 no.5
• /
• pp.447-453
• /
• 2009

This paper introduces the method for detect voices and exact end point at low SNR by maximizing voice energy. Conventional VAD (Voice Activity Detection) algorithm estimates noise level so it tends to detect the end point inaccurately. Moreover, because it uses relatively long analysis range for reflecting temporal change of noise, computing load too high for application. In this paper, the SEM-VAD (Speech Energy Maximization-Voice Activity Detection) method which uses psycho-acoustical bark scale filter banks to maximize voice energy within frames is introduced. Stable threshold values are obtained at various noise environments (SNR 15 dB, 10 dB, 5 dB, 0 dB). At the test for voice detection in car noisy environment, PHR (Pause Hit Rate) was 100%accurate at every noise environment, and FAR (False Alarm Rate) shows 0% at SNR15 dB and 10 dB, 5.6% at SNR5 dB and 9.5% at SNR0 dB.

• Korean Journal of Bronchoesophagology
• /
• v.7 no.2
• /
• pp.161-167
• /
• 2001

Background and Objectives： Total laryngectomy is often required for advanced cases. But this operation induced the many inconvenience of basic daily life. Early diagnosis of laryngeal cancer is very important to prevent from this disastrous condition. In this point of view, mass screening test for early detection of laryngeal cancer is necessary. Screening test using voice has many advantages such as simple, less interventional. Voice collection by Automatic Response System(ARS) is comfortable and easy to got acoustic sample. Thus author tried to got the acoustic parameters which can differentiate normal, benign. and malignant laryngeal diseases and also checked the availability of parameters on neural network system. Materials and Methods: Author has evaluated the voice from 17 laryngeal cancer patients and 45 benign laryngeal disease patients who visited at Department of Otolaryngology, Pusan National University Hospital from May 1998 to April 2001, and 15 normal control. Author chose the sir Parameters (Jitt. vFo, Shim, vAm, NHR, SPI) that was thought to be related with voice collected by ARS among thirty-three parameters analysed by a Multi-Dimensional Voice Program (MDVP). Two-step neural network was used for the availability of six parameters. Results: The detection rate of normal voice by ARS voice analysis is 78.5% and detection rate of abnormal voice was 97.1 o/o. Among abnormal voice, the detection rate of benign laryngeal diseases and laryngeal cancers were 82.4 o/o, 70.6% respectively. Conclusion: Author concluded that six parameters and Matlab based neural network software may be effective in development of acoustic screening system for laryngeal cancer and further study should be necessary for development of new acoustic parameters.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.22 no.6
• /
• pp.1302-1310
• /
• 1997

In this paper, we propose a dynamic code allocation strategy using voice activity detection and evaluate the performance of a dynamic code allocation strategy using voice activeity detection in DS-CDMA system. Proposed method allocates code to mobile terminal according to the residual capacity computed by SIR in the base station. In hot spot traffic loading cell, we find that the performance of proposed method is better than that of a fixed code assignment strategy using voice activity detection. Also, we find that the proposed method provide much improvement in blocking probability against the dynamic code assignment strategy withoug voice activity detection.

• Proceedings of the Acoustical Society of Korea Conference
• /
• spring
• /
• pp.25-28
• /
• 2002

Voice activity detection is important Problem in the speech recognition and communication. This paper introduces feature parameter which is reconstructed by the spectral entropy of information theory for the robust voice activity detection in the noise environment, analyzes and compares it with the energy method of voice activity detection and performance. In experiment, we confirmed that the spectral entropy is more feature parameter than the energy method for the robust voice activity detection in the various noise environment.

• Journal of Korea Multimedia Society
• /
• v.4 no.1
• /
• pp.46-55
• /
• 2001

In this paper, a new voice activity detection method estimating SNR of enhanced speech with extended spectral subtraction (ESS) is proposed. Voice activity detection is performed by putting an second Wiener filter behind an Wiener filter used in the ESS to estimate speech and noise power of output signal of first Wiener filter. The proposed voice activity detection method does not require many computational loads and performs well under severe input SNR. Boll's spectral substraction algorithm with proposed voice activity detection was compared to ESS under several noise environment having different time-frequency distributions. During speech and non-speech activity, performance of Boll's spectral substraction algorithm with proposed voice activity detection is superior to that of ESS.

• Journal of the Institute of Convergence Signal Processing
• /
• v.9 no.2
• /
• pp.121-128
• /
• 2008

Accurate voice activity detection have a great impact on performance of speech applications including speech recognition, speech coding, and speech communication. In this paper, we propose methods for voice activity detection that can adapt to various car noise situations during driving. Existing voice activity detection used various method such as time energy, frequency energy, zero crossing rate, and spectral entropy that have a weak point of rapid. decline performance in noisy environments. In this paper, the approach is based on existing spectral entropy for VAD that we propose voice activity detection method using MFB(Met-frequency filter banks) spectral entropy, gradient FFT(Fast Fourier Transform) spectral entropy. and gradient MFB spectral entropy. FFT multiplied by Mel-scale is MFB and Mel-scale is non linear scale when human sound perception reflects characteristic of speech. Proposed MFB spectral entropy method clearly improve the ability to discriminate between speech and non-speech for various in noisy car environments that achieves 93.21% accuracy as a result of experiments. Compared to the spectral entropy method, the proposed voice activity detection gives an average improvement in the correct detection rate of more than 3.2%.

• Journal of Korea Multimedia Society
• /
• v.16 no.9
• /
• pp.1005-1017
• /
• 2013

Voice activity detection is very important process that voice activity separated form noisy speech signal for speech enhance. Over the past few years, many studies have been made on voice activity detection, but it has poor performance in low signal to noise ratio environment or fickle noise such as car noise. In this paper, it proposed new voice activity detection algorithm using ensemble variance based on wavelet band entropy and soft thresholding method. We conduct a survey in a lot of signal to noise ratio environment of car noise to evaluate performance of the proposed algorithm and confirmed performance of the proposed algorithm.

• Proceedings of the IEEK Conference
• /
• 2003.11a
• /
• pp.61-64
• /
• 2003

In this paper, we implement PAMD(Positive Answering Machine Detection) for discrimination human and ARS. We are used Grunt detection, Glitch Noise detection and Tone detection for PAMD. It distinguishes voice signals from ring-back tone and glitch noise respectively. And as a second step, it judges whether human responses or ARS responses after integrating pattern changes like initial response period, the number of voice data, each time of voice data period and glitch noise. The accuracy is about 9375 in ASR and about 98％ in Mobile phone.

• Journal of Digital Convergence
• /
• v.14 no.11
• /
• pp.249-255
• /
• 2016

Since the elderly voices include a lot of noise caused by physiological changes in respiration, phonation, and resonance, the performance of the convergence health-care equipments such as speech recognition, synthesis, analysis program done by elderly voice is deteriorated. Therefore it is necessary to develop researches to operate health-care instruments with elderly voices. In this study, a voice activity detection using a symmetric higher-order differential energy function (SHODEO) was developed and was compared with auto-correlation function(ACF) and the average magnitude difference function(AMDF). It was confirmed to have a better performance than other methods in the voice interval detection. The voice activity detection will be applied to a voice interface for the elderly to improve the accessibility of the smart devices.