Go to the main menu
Skip to content
Go to bottom
REFERENCE LINKING PLATFORM OF KOREA S&T JOURNALS
> Journal Vol & Issue
The Journal of the Acoustical Society of Korea
Journal Basic Information
Journal DOI :
The Acoustical Society of Korea
Editor in Chief :
Volume & Issues
Volume 13, Issue 6 - Dec 1994
Volume 13, Issue 5 - Oct 1994
Volume 13, Issue 4 - Aug 1994
Volume 13, Issue 3 - Jun 1994
Volume 13, Issue 2 - Apr 1994
Volume 13, Issue 1 - Feb 1994
Volume 13, Issue 2E - 00 1994
Volume 13, Issue 1E - 00 1994
Selecting the target year
Numerical Analysis of Multi-Layer Multi-Coupled Microstrip Lines
Seo, Cheol-Heon ;
The Journal of the Acoustical Society of Korea, volume 13, issue 1E, 1994, Pages 5~5
It is obtained the general expessions of the numerical method are applied for the TEM-mode analysis of multu-layer multi-coupled microstrip lines, In this paper, coupled microstrip are replaced by three-coupled microstrip lines in special aplications. Three-layer versions of three-coupled microstrip lines are specially attactive because of the additional flexibilities offered by three-layer configuration. This structure can be used for obtaining large capacitance and preventing coupling among microstrip lines in filter and coupler. Sappihre is chosen for anisotropic substrates material. The permittivity parallel to the optical axis is higher than the permittivity in the plane perpendicular to this axis.
HMM with Global Path constraint in Viterbi Decoding for Insolated Word Recognition
Kim, Weon-Goo ; Ahn, Dong-Soon ; Youn, Dae-Hee ;
The Journal of the Acoustical Society of Korea, volume 13, issue 1E, 1994, Pages 11~11
Hidden Markov Models (HMM's) with explicit state duration density (HMM/SD) can represent the time-varying characteristics of speech signals more accurately. However, such an advantage is reduced in relatively smooth state duration densities or ling bounded duration. To solve this problem, we propose HMM's with global path constraint (HMM/GPC) where the transition between states occur only within prescribed time slots. HMM/GPC explicitly limits state durations and accurately describes the temproal structure of speech simply and efficiently. HMM's formed by combining HMM/GPC with HMM/SD are also presented (HMM/SD+GPC) and performances are compared. HMM/GPC can be implemented with slight modifications to the conventional Viterbi algorithm. HMM/GPC and HMM/SD_GPC not only show superior performance than the conventional HMM and HMM/SD but also require much less computation. In the speaket independent isolated word recognition experiments, the minimum recognition eror rate of HMM/GPC(1.6%) is 1.1% lower than the conventional HMM's and the required computation decreased about 57%.
A New Speech Recognition Model : Dynamically Localized Self-organizing Map Model
Na, Kyung-Min ; Rheem, Jae-Yeol ; Ann, Sou-Guil ;
The Journal of the Acoustical Society of Korea, volume 13, issue 1E, 1994, Pages 20~20
A new speech recognition model, DLSMM(Dynamically Localized Self-organizing Map Model) and its effective training algorithm are proposed in this paper. In DLSMM, temporal and spatial distortions of speech are efficiently normalized by dynamic programming technique and localized self-organizing maps, respectively. Experiments on Korean digits recognition have been carried out. DLSMM has smaller Experiments on Korean digits recognition have been carried out. DLSMM has smaller connections than predictive neural network models, but it has scored a little high recognition rate.
Self-Adaptive Learning Algorithm for Training Multi-Layered Neural Networks and Its Applications
Cheung, Wan-Sup ; Jho, Moon-Jae ; Hammond, Joseph K. ;
The Journal of the Acoustical Society of Korea, volume 13, issue 1E, 1994, Pages 25~25
A problem of making a neural network learning self-adaptive to the training set supplied is addressed in this paper. This arises from the aspect in choice of an adequate stepsize for the update of the current weigh vectors according to the training pairs. Related issues in this attempt are raised and fundamentals in neural network learning are introduced. In comparison to the most popular back-propagation scheme, the usefulness and superiority of the proposed weight update algorithm are illustrated by examing the identification of unknown nonlinear systems only from measurements.
A New Method for Measuring the Distortions of Electrodynamic Loudspeaker at Low Frequencies Part 1 : Closed-Bow Loudspeaker
Doo, Se-Jin ; Sung, Koeng-Mo ;
The Journal of the Acoustical Society of Korea, volume 13, issue 1E, 1994, Pages 37~37
A method for measuring the loudspeaker distortions at low frequencies without an anechoic is proposed. This method is based on the fact that the n-th harmonic distortion outside the enclosure is boosted by 40log n dB compared to that inside the enclosure. The applicable frequency range is extended by cancelling the effect of standing wave inside the enclosure. Causes of measurement error are also analyzed.
Determination of the Optimal Crystal Cut and Propagation Direction of a Piezoelectric Substrate for SAW Devices
Roh, Yong-Rae ; Bae, Young-Ho ; Chung, Dae-Sik ;
The Journal of the Acoustical Society of Korea, volume 13, issue 1E, 1994, Pages 45~45
Characteristics of a piezoelectric material are evaluated to pick up the optimal crystal cut and propagation direction for a SAW device. For the piezoelectric single crystal
, such items are investigated as the Rayleigh wave velocity, the electromechanical coupling factor, the surface permittivity, the frequency-temperature coefficient, the air loading attenuation, the pure mode propagation, the beam steering and the misalignment sensitivity. Theoretical calculations reveal that Y-cut and Z-propagation is the optimal SAW propagation path. The results are confirmed through experiments. The method empolyed in this paper is applicable to other crystals, too, either single or poly crystals.
A Decision-Theoretic Approach to Source Direction Finding Based on the Hopfield Neural Network
Cheung, Wan-Sup ; Jho, Moon-Je ; Eun, Hui-Joon ;
The Journal of the Acoustical Society of Korea, volume 13, issue 1E, 1994, Pages 55~55
A decision-theretic concept is introduced to investigate whether targets of interest in array sensor systems are present at some steering direction or not. The solutions to this problem are described as a set of discrete numbers 0 or 1 corresponding to the direction under consideration. This coded number representation is transplanted in the optimisation technique based on the Hopfield neural network, which may provide an easy understanding of determining the direction of arrival (DOA) of sources. Difficulties encountered in using the conventional state schemes of Hopfield neural network models are addressed and their related issues are raised. To deal with them, an idea that a neuron that decreases more energy difference for its state change of 0 to 1can have higher priority in the order of state transition than others is introduced. This does not only lead to an new state update scheme but also opens a different story in comparison to previous work. To cast the perspectives of the proposed approach and illustrate its effectiveness in source direction finding in array sensor system. simulation results and related discussions are presented in this paper.
Discriminative Training of Predictive Neural Network Models
Na, Kyung-Min ; Rheem, Jae-Yeol ; Ann, Sou-Guil ;
The Journal of the Acoustical Society of Korea, volume 13, issue 1E, 1994, Pages 64~64
Predictive neural network models are powerful speech recognition models based on a nonlinear pattern prediction. But those models suffer from poor discrimination between acoustically similar words. In this paper we propose an discriminative training algorithm for predictive neural network models. This algorithm is derived from GPD (Generalized Probabilistic Descent) algorithm coupled with MCEF(Minimum Classification Error Formulation). It allows direct minimization of a recognition error rate. Evaluation of our training algoritym on ten Korean digits shows its effectiveness by 30% reduction of recognition error.
Pseudo-Cepstral Representation of Speech Signal and Its Application to Speech Recognition
Kim, Hong-Kook ; Lee, Hwang-Soo ;
The Journal of the Acoustical Society of Korea, volume 13, issue 1E, 1994, Pages 71~71
In this paper, we propose a pseudo-cepstral representation of line spectrum pair(LSP) frequencies and evaluate speech recognition performance with cepstral lift using the pseudo-cepstrum. The pseudo-cepstrum corresponding to LSP frequencies is derived by approxmating the relationship between LPC-cepstrum and LSP frequencies. Three cepstral liftering procedures are applied to the pseudo-cepstrum to improve the performance of speech recognition. They are the root-power-sums ligter, the general exponential lifter, and the bandpass lifter. Then, the liftered psedudo-cepstra are warped into a mel-frequency scale to obtain feature vectors for speech recognition. Among the three lifters, the general exponential lifter results in the best performance on speech recognition. When we use the proposed pseudo-cepstra feature vectors for recognizing noisy speech, the signal-to-noise ratio (SNR) improvement of about 5~10dB LSP is obtained.
Detection of Glottal Closure Instant using the property of G-peak
Keum, Hong ; Kim, Dae-Sik ; Bae, Myung-Jin ; Kim, Young-Il ;
The Journal of the Acoustical Society of Korea, volume 13, issue 1E, 1994, Pages 82~82
It is important to exactly detect the GCI(Glottal Closure Instant) in the speech signal processing. A few methods to detect the GCI of voiced speech have een proposer, untill now. But these are difficult to detect the GCI for wide range of speakers and or various vowel signals. In this paper, we prposed a new method for GCI detection using the G-peak. The speech waveforms are passed through the LPF of variable bandwidth. Then, the GCI's of voiced speech are detected by the G-peak based on the filtered signals. We compared the detected with the eye-checked GCI at the SNR of clean, 20dB, and 0dB. We took into account the range within 1ms between eye-checked and detected GCI. We obtained the result of the detection rate as 97.9% in the clean speech, 96.5% in 20dB SNR, and 94.8% in 0dB SNR, respectively.
Development of a Read-time Voice Dialing System Using Discrete Hidden Markov Models
Lee, Se-Woong ; Choi, Seung-Ho ; Lee, Mi-Suk ; Kim, Hong-Kook ; Oh, Kwang-Cheol ; Kim, Ki-Chul ; Lee, Hwang-Soo ;
The Journal of the Acoustical Society of Korea, volume 13, issue 1E, 1994, Pages 89~89
This paper describes development of a real-time voice dialing system which can recognize around one hundred word vocabularies in speaker independent mode. The voice recognition algorithm in this system is implemented on a DSP board with a telephone interface plugged in an IBM PC AT/486. In the DSP board, procedures for feature extraction, vector quantization(VQ), and end-point detection are performed simultaneously in every 10 msec frame interval to satisfy real-time constraints after detecting the word starting point. In addition, we optimize the VQ codebook size and the end-point detection procedure to reduce recognition time and memory requirement. The demonstration system has been displayed in MOBILAB of the Korean Mobile Telecom at the Taejon EXPO'93.