• Journal of the Korean Society of Laryngology, Phoniatrics and Logopedics
• /
• v.14 no.2
• /
• pp.110-116
• /
• 2003

Background and Objectives : Laryngeal cancer discrimination using voice signals is a non-invasive method that can carry out the examination rapidly and simply without giving discomfort to the patients. n appropriate analysis parameters and classifiers are developed, this method can be used effectively in various applications including telemedicine. This study examines voice analysis parameters used for laryngeal disease discrimination to help discriminate laryngeal diseases by voice signal analysis. The study also estimates the laryngeal cancer discrimination activity of the Gaussian mixture model (GMM) classifier based on the statistical modelling of voice analysis parameters. Materials and Methods : The Multi-dimensional voice program (MDVP) parameters, which have been widely used for the analysis of laryngeal cancer voice, sometimes fail to analyze the voice of a laryngeal cancer patient whose cycle is seriously damaged. Accordingly, it is necessary to develop a new method that enables an analysis of high reliability for the voice signals that cannot be analyzed by the MDVP. To conduct the experiments of laryngeal cancer discrimination, the authors used three types of voices collected at the Department of Otorhinorlaryngology, Pusan National University Hospital. 50 normal males voice data, 50 voices of males with benign laryngeal diseases and 105 voices of males laryngeal cancer. In addition, the experiment also included 11 voices data of males with laryngeal cancer that cannot be analyzed by the MDVP, Only monosyllabic vowel /a/ was used as voice data. Since there were only 11 voices of laryngeal cancer patients that cannot be analyzed by the MDVP, those voices were used only for discrimination. This study examined the linear predictive cepstral coefficients (LPCC) and the met-frequency cepstral coefficients (MFCC) that are the two major cepstrum analysis methods in the area of acoustic recognition. Results : The results showed that this met frequency scaling process was effective in acoustic recognition but not useful for laryngeal cancer discrimination. Accordingly, the linear frequency cepstral coefficients (LFCC) that excluded the met frequency scaling from the MFCC was introduced. The LFCC showed more excellent discrimination activity rather than the MFCC in predictability of laryngeal cancer. Conclusion : In conclusion, the parameters applied in this study could discriminate accurately even the terminal laryngeal cancer whose periodicity is disturbed. Also it is thought that future studies on various classification algorithms and parameters representing pathophysiology of vocal cords will make it possible to discriminate benign laryngeal diseases as well, in addition to laryngeal cancer.

• The Journal of the Acoustical Society of Korea
• /
• v.38 no.1
• /
• pp.39-46
• /
• 2019

In this paper, combining features is proposed as a way to enhance the classification accuracy of sounds under noisy environments using the CNN (Convolutional Neural Network) structure. A robust log Mel-filter bank using Wiener filter and PNCCs (Power Normalized Cepstral Coefficients) are extracted to form a 2-dimensional feature that is used as input to the CNN structure. An ebird database is used to classify 43 types of bird species in their natural environment. To evaluate the performance of the combined features under noisy environments, the database is augmented with 3 types of noise under 4 different SNRs (Signal to Noise Ratios) (20 dB, 10 dB, 5 dB, 0 dB). The combined feature is compared to the log Mel-filter bank with and without incorporating the Wiener filter and the PNCCs. The combined feature is shown to outperform the other mentioned features under clean environments with a 1.34 % increase in overall average accuracy. Additionally, the accuracy under noisy environments at the 4 SNR levels is increased by 1.06 % and 0.65 % for shop and schoolyard noise backgrounds, respectively.

• The Journal of the Acoustical Society of Korea
• /
• v.29 no.4
• /
• pp.243-250
• /
• 2010

This paper proposes a spectral modeling of Korean traditional instrument, Haegeum, using cepstral analysis to naturally describe Haegeum sounds varying with time. To get a precise result of cepstral analysis, we set the frame size to 3 periods of input signal and more cepstral coefficients are used to extract formants. The performance is enhanced by flexibly controlling the cutoff frequency of bandpass filter depending on the resonances in the synthesis process of sinusoidal components and the deleting peaks remained in the residual signal. To detect the change of pitch, we divide the input frames into silence, attack, and sustain region and determine which region the current frame is involved in. Then, the proposed method readjusts the frame size according to the fundamental frequency in the case of the current frame is in attack region and corrects the extraction errors of the fundamental frequency for the frames in sustain region. With these processes, the synthesized sounds are much more similar to the originals. The evaluation result through the listening test by a Haegeum player says that the synthesized sounds are almost similar to originals (96~100 % similar to the original sounds).

• Journal of the Korean Society of Industry Convergence
• /
• v.21 no.1
• /
• pp.17-27
• /
• 2018

We propose a new approach to control a biped robot motion based on iterative learning of voice command for the implementation of smart factory. The real-time processing of speech signal is very important for high-speed and precise automatic voice recognition technology. Recently, voice recognition is being used for intelligent robot control, artificial life, wireless communication and IoT application. In order to extract valuable information from the speech signal, make decisions on the process, and obtain results, the data needs to be manipulated and analyzed. Basic method used for extracting the features of the voice signal is to find the Mel frequency cepstral coefficients. Mel-frequency cepstral coefficients are the coefficients that collectively represent the short-term power spectrum of a sound, based on a linear cosine transform of a log power spectrum on a nonlinear mel scale of frequency. The reliability of voice command to control of the biped robot's motion is illustrated by computer simulation and experiment for biped walking robot with 24 joint.

• The Journal of the Acoustical Society of Korea
• /
• v.26 no.6
• /
• pp.243-249
• /
• 2007

We propose an effective voice-based gender identification using group delay(GD) Generally, features for speech recognition are composed of magnitude information rather than phase information. In our approach, we address a difference between male and female for GD which is a derivative of the Fourier transform phase. Also, we propose a novel way to incorporate the features fusion scheme based on a combination of GD and magnitude information such as mel-frequency cepstral coefficients(MFCC), linear predictive coding (LPC) coefficients, reflection coefficients and formant. The experimental results indicate that GD is effective in discriminating gender and the performance is significantly improved when the proposed feature fusion technique is applied.

• Journal of the Korea Society of Computer and Information
• /
• v.18 no.7
• /
• pp.23-35
• /
• 2013

This paper proposes an effective technique that is used to automatically extract feature vectors from vibration signals for fault classification systems. Conventional mel-frequency cepstral coefficients (MFCCs) are sensitive to noise of vibration signals, degrading classification accuracy. To solve this problem, this paper proposes spectral envelope cepstral coefficients (SECC) analysis, where a 4-step filter bank based on spectral envelopes of vibration signals is used: (1) a linear predictive coding (LPC) algorithm is used to specify spectral envelopes of all faulty vibration signals, (2) all envelopes are averaged to get general spectral shape, (3) a gradient descent method is used to find extremes of the average envelope and its frequencies, (4) a non-overlapped filter is used to have centers calculated from distances between valley frequencies of the envelope. This 4-step filter bank is then used in cepstral coefficients computation to extract feature vectors. Finally, a multi-layer support vector machine (MLSVM) with various sigma values uses these special parameters to identify faulty types of induction motors. Experimental results indicate that the proposed extraction method outperforms other feature extraction algorithms, yielding more than about 99.65% of classification accuracy.

• Journal of IKEEE
• /
• v.2 no.1 s.2
• /
• pp.61-67
• /
• 1998

In this thesis, experiment have performed with the speaker recognition using multilayer feedforward neural network(MFNN) model using Korean and Japanese digits . The 5 adult males and 5 adult females pronounciate form 0 to 9 digits of Korean, Japanese 7 times. And then, they are extracted characteristics coefficient through Pitch deletion algorithm, LPC analysis, and LPC Cepstral analysis to generate input pattern of MFNN. 5 times among them are used to train a neural network, and 2 times is used to measure the performance of neural network. Both Korean and Japanese, Pitch coefficients is about 4%t more enhanced than LPC or LPC Cepstral coefficients.

• Journal of IKEEE
• /
• v.22 no.3
• /
• pp.624-629
• /
• 2018

Classification of moving targets in Pulse Doppler Radar(PDR) for surveillance and reconnaissance purposes is generally carried out based on listening and training experience of Doppler audio signals by radar operator. In this paper, we proposed the automatic classification method to identify the class of moving target with Doppler audio signals using the Mel Frequency Cepstral Coefficients(MFCC) and the Hidden Markov Model(HMM) algorithm which are widely used in speech recognition and the classification performance was analyzed and verified by simulations.

• Journal of the Institute of Electronics Engineers of Korea TE
• /
• v.39 no.2
• /
• pp.60-65
• /
• 2002

In this paper, we propose GFCC(gammatone filter frequency cepstrum coefficient) parameter which was based on the auditory characteristic for accomplishing better speech recognition rate. And it is performed the experiment of speech recognition for isolated word acquired from telephone network. For the purpose of comparing GFCC parameter with other parameter, the experiment of speech recognition are carried out using MFCC and LPCC parameter. Also, for each parameter, we are implemented CMS(cepstral mean subtraction)which was applied or not in order to compensate channel distortion in telephone network. Accordingly, we found that the recognition rate using GFCC parameter is better than other parameter in the experimental result.

• Journal of Information Processing Systems
• /
• v.14 no.4
• /
• pp.807-823
• /
• 2018

Speaker verification system performance depends on the utterance of each speaker. To verify the speaker, important information has to be captured from the utterance. Nowadays under the constraints of limited data, speaker verification has become a challenging task. The testing and training data are in terms of few seconds in limited data. The feature vectors extracted from single frame size and rate (SFSR) analysis is not sufficient for training and testing speakers in speaker verification. This leads to poor speaker modeling during training and may not provide good decision during testing. The problem is to be resolved by increasing feature vectors of training and testing data to the same duration. For that we are using multiple frame size (MFS), multiple frame rate (MFR), and multiple frame size and rate (MFSR) analysis techniques for speaker verification under limited data condition. These analysis techniques relatively extract more feature vector during training and testing and develop improved modeling and testing for limited data. To demonstrate this we have used mel-frequency cepstral coefficients (MFCC) and linear prediction cepstral coefficients (LPCC) as feature. Gaussian mixture model (GMM) and GMM-universal background model (GMM-UBM) are used for modeling the speaker. The database used is NIST-2003. The experimental results indicate that, improved performance of MFS, MFR, and MFSR analysis radically better compared with SFSR analysis. The experimental results show that LPCC based MFSR analysis perform better compared to other analysis techniques and feature extraction techniques.