• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.11 no.4
• /
• pp.287-295
• /
• 1986

In this paper, a SBC(sub-band-coding) is proposed to code a speech signal for a digital mobile radio and a robustness of speech quality of the SBC over the Rayleigh fading channel is investigated via a computer simulation. First the Rayleigh fading channel and 16-ary DPSK receiver models are presentes and verified its validitties by comparing with theoretical values. Three different measures: SNR, LPC distance measure and subjective listening test, were used to evaluate the effects due to the Rayleigh fading channel errors. From the results of computer simulation at BER=$10_{-3}$, $10_{-2}$, 5$ imes$$10_{-2}$, it was found that the speech remained quite intelligible at BER=$10_{-2}$and the link is still usuable even at BER=5$ imes$$10_{-2}$ Thus it was concluded that the SBC can be applicable to the digital mobile radio on the Rayleigh fading channel error in the range of $10_{-4}$~$10_{-2}$ without emplowing any error correction codes.

• The Journal of the Acoustical Society of Korea
• /
• v.17 no.2E
• /
• pp.31-37
• /
• 1998

This paper proposes a feature extraction method using wavelet transform for speech recognition. Speech recognition system generally carries out the recognition task based on speech features which are usually obtained via time-frequency representations such as Short-Time Fourier Transform (STFT) and Linear Predictive Coding(LPC). In some respects these methods may not be suitable for representing highly complex speech characteristics. They map the speech features with same may not frequency resolutions at all frequencies. Wavelet transform overcomes some of these limitations. Wavelet transform captures signal with fine time resolutions at high frequencies and fine frequency resolutions at low frequencies, which may present a significant advantage when analyzing highly localized speech events. Based on this motivation, this paper investigates the effectiveness of wavelet transform for feature extraction of wavelet transform for feature extraction focused on enhancing speech recognition. The proposed method is implemented using Sampled Continuous Wavelet Transform (SCWT) and its performance is tested on a speaker-independent isolated word recognizer that discerns 50 Korean words. In particular, the effect of mother wavelet employed and number of voices per octave on the performance of proposed method is investigated. Also the influence on the size of mother wavelet on the performance of proposed method is discussed. Throughout the experiments, the performance of proposed method is discussed. Throughout the experiments, the performance of proposed method is compared with the most prevalent conventional method, MFCC (Mel0frequency Cepstral Coefficient). The experiments show that the recognition performance of the proposed method is better than that of MFCC. But the improvement is marginal while, due to the dimensionality increase, the computational loads of proposed method is substantially greater than that of MFCC.

• 제어로봇시스템학회:학술대회논문집
• /
• 2004.08a
• /
• pp.1033-1036
• /
• 2004

The study on speech recognition and understanding has been done for many years. In this paper, we propose a new type of recurrent neural network architecture for speech recognition, in which each output unit is connected to itself and is also fully connected to other output units and all hidden units [1]. Besides that, we also proposed the new architecture and the learning algorithm of recurrent neural network such as Backpropagation Through Time (BPTT, which well-suited. The aim of the study was to observe the difference of Arabic's alphabet like "alif" until "ya". The purpose of this research is to upgrade the people's knowledge and understanding on Arabic's alphabet or word by using Recurrent Neural Network (RNN) and Backpropagation Through Time (BPTT) learning algorithm. 4 speakers (a mixture of male and female) are trained in quiet environment. Neural network is well-known as a technique that has the ability to classified nonlinear problem. Today, lots of researches have been done in applying Neural Network towards the solution of speech recognition [2] such as Arabic. The Arabic language offers a number of challenges for speech recognition [3]. Even through positive results have been obtained from the continuous study, research on minimizing the error rate is still gaining lots attention. This research utilizes Recurrent Neural Network, one of Neural Network technique to observe the difference of alphabet "alif" until "ya".

• Proceedings of the KIEE Conference
• /
• 2004.11c
• /
• pp.310-312
• /
• 2004

The aim of this study was to analyze the characteristics of knee joint sound in frequency domain and classify the knee joint diseases. The spectral analysis of knee joint sounds was performed using LPC(Linear Predictive Coding) and Wigner-Ville distribution. Ten normal subjects and 5 patients with meniscal tearing were enrolled. Each subject was seated on a chair and underwent active knee flexion and extension for 60 seconds. Sampling frequency was 10kHz and electronic stethoscope and electro-goniometer were applied during the knee motion for data collection. The spectral analysis showed 3 peaks in both groups and the difference energy distribution in time-frequency domain. These results suggest that the diagnosis of knee joint pathology using the auscultation could be easier and more correct.

• Transactions of the Korean Society for Noise and Vibration Engineering
• /
• v.21 no.11
• /
• pp.1020-1028
• /
• 2011

As rotating machines play an important role in industrial applications such as aeronautical, naval and automotive industries, many researchers have developed various condition monitoring system and fault diagnosis system by applying artificial neural network. Since using obtained signals without preprocessing as inputs of neural network can decrease performance of fault classification, it is very important to extract significant features of captured signals and to apply suitable features into diagnosis system according to the kinds of obtained signals. Therefore, this paper proposes a neural-network-based fault diagnosis system using AR coefficients as feature vectors by LPC(linear predictive coding) and EIV(errors-in variables) analysis. We extracted feature vectors from sound, vibration and current faulty signals and evaluated the suitability of feature vectors depending on the classification results and training error rates by changing AR order and adding noise. From experimental results, we conclude that classification results using feature vectors by EIV analysis indicate more than 90 % stably for less than 10 orders and noise effect comparing to LPC.

• Speech Sciences
• /
• v.10 no.2
• /
• pp.99-109
• /
• 2003

The purpose of this study was to analyze and compare head register with chest register of singers acoustically. Fifteen healthy tenor major students were participated. Fifteen healthy untrained adults were chosen as the control group for this study. Long term average (LTA) power spectrum using the Fast Fourier transform (FFT) algorithm and Linear predictive coding (LPC) filter response were made with /a/ sustained in both head (G4, 392 Hz) and chest registers (C3, 131 Hz). Statistical analysis was performed using the Mann-Whitney test. In the LTA power spectrum, head register of singers increased in the level of energy gain within the frequency of 2.2-3.4 kHz (p<0.01), and 7.5-8.4 kHz (p<0.01, p<0.05). Chest register of singers increased in the frequency of 2.2-3.1 kHz (p<0.01), 7.8-8.4 kHz (p<0.05) and around 9.6 kHz (p<0.01). The LTA power spectrum revealed a peak of acoustic energy around 2,500 Hz, known as the singer's formant and another peak of acoustic energy around 8,000 Hz in the singer's voice.

• Journal of Korea Multimedia Society
• /
• v.20 no.11
• /
• pp.1811-1819
• /
• 2017

As the induction motor is the core production equipment of the industry, it is necessary to construct a fault prediction and diagnosis system through continuous monitoring. Many researches have been conducted on motor fault diagnosis algorithm based on signal processing techniques using Fourier transform, neural networks, and fuzzy inference techniques. In this paper, we propose a fault diagnosis method of induction motor using LPC and DNN. To evaluate the performance of the proposed method, the fault diagnosis was carried out using the vibration data of the induction motor in steady state and simulated various fault conditions. Experimental results show that the learning time of our proposed method and the conventional spectrum+DNN method is 139 seconds and 974 seconds each executed on the experimental PC, and our method reduces execution time by 1/8 compared with conventional method. And the success rate of the proposed method is 98.08%, which is similar to 99.54% of the conventional method.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.17 no.4
• /
• pp.775-780
• /
• 2013

This paper proposes a speaker-dependent speech recognition algorithm which can classify the gender for male and female speakers in white noise and car noise, using a neural network. The proposed speech recognition algorithm is trained by the neural network to recognize the gender for male and female speakers, using LPC (Linear Predictive Coding) cepstrum coefficients. In the experiment results, the maximal improvement of total speech recognition rate is 96% for white noise and 88% for car noise, respectively, after trained a total of six neural networks. Finally, the proposed speech recognition algorithm is compared with the results of a conventional speech recognition algorithm in the background noisy environment.

• Journal of the Korean Society of Laryngology, Phoniatrics and Logopedics
• /
• v.13 no.1
• /
• pp.52-58
• /
• 2002

The pitch range of the human voice is variable, extending from chest register to falsetto. Although numerous studies have investigated after laryngeal mechanism description of registers, systematic and objective studies were lack. The purpose of this study was to analyze and compare head register with chest register of singers acoustically. Fifteen healthy tenor major students were selected. Fifteen healthy untrained adults were the control group for this study. Long term average(LTA) power spectrum using the Fast Fourier transform(FFT) algorithm and Linear predictive coding (LPC) filter response were made during /a/ sustained in both head(G4, 392Hz) md chest registers (C3, 131Hz). Statistical analysis was performed using Mann-Whitney test. In the LTA power spectrum, head register of singer has increased level(energy gain) in the frequency band of 2.2-3.4kHz(p<0.01), and 7.5-8.4kHz(p<0.01, p<0.05). Chest register of singer has increased level in the frequency band of 2.2-3.1kHz(p<0.01), 7.8-8.4kHz(p<0.05) and around 9.6kHz(p<0.01). LTA power spectrum reveals a peak of acoustic energy around 2500Hz known as the singer's formant and another peak of acoustic energy around 8000Hz in singer's voice.

• Convergence Security Journal
• /
• v.8 no.4
• /
• pp.135-143
• /
• 2008

Currently, The HMI system is being used on the network is limited in the ability. In this paper, an Industrial HMI applied the transformed state splitting algorithm. this study suggests by applying a transformed the Successive state splitting algorithm, for the modeling in the questions of the expected data. So, you can save time and reliable and precise as high as 98.15 percent repregented recognition rate. HMI system applied to the voice of industrial equipment the man can not act directly in the industry environment was able to drive devices. Optimize the performance of the engine was the voice of HMI system.