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 15, Issue 6 - Dec 1996
Volume 15, Issue 5 - Oct 1996
Volume 15, Issue 4 - Aug 1996
Volume 15, Issue 2 - Apr 1996
Volume 15, Issue 1 - Feb 1996
Volume 15, Issue 4E - 00 1996
Volume 15, Issue 3E - 00 1996
Volume 15, Issue 2E - 00 1996
Volume 15, Issue 1E - 00 1996
Selecting the target year
A Study on the Speaker Adaptation of a Continuous Speech Recognition using HMM
Kim, Sang-Bum ; Lee, Young-Jae ; Koh, Si-Young ; Hur, Kang-In ;
The Journal of the Acoustical Society of Korea, volume 15, issue 4, 1996, Pages 5~11
In this study, the method of speaker adaptation for uttered sentence using syllable unit hmm is proposed. Segmentation of syllable unit for sentence is performed automatically by concatenation of syllable unit hmm and viterbi segmentation. Speaker adaptation is performed using MAPE(Maximum A Posteriori Probabillity Estimation) which can adapt any small amount of adaptation speech data and add one sequentially. For newspaper editorial continuous speech, the recognition rates of adaptation of HMM was 71.8% which is approximately 37% improvement over that of unadapted HMM
Physical Characteristics of Noise of the High-Speed Train and the Evaluation of the Exterior Noise around Stations
Lee, Sang-Woo ; Goo, Jae-Oh ; Han, Chan-Hoon ;
The Journal of the Acoustical Society of Korea, volume 15, issue 4, 1996, Pages 12~17
With the increase in discomfort of living by serious traffic noise pollution, the desire of relieving from discomfort is boosted up more than ever. For this reason, the researches on environmental impact assessmient and noise pollution control are highly required. This research was aimed to analyze the physical characteristics of noise caused by high-speed train in foreign countries by literature survey and field data. And with the attained results, the exterior noise level around Chon-An station, the first station planned for the high-speed train in this country, was estimated. The results of this study might be used as a tool for predicting the unavoidable noise, lessening the noise impact caused by the high-speed train, and preparing the noise prevention measures for the interior space and the exterior around stations.
Statistical Characteristics of Bottom Backscattering by a Moving Source at a Shallow Water Site
Park, J.S. ; Jurng, M.S. ; Chang, D.H. ; Choi, J.Y. ; Shim, Tae-Bo ;
The Journal of the Acoustical Society of Korea, volume 15, issue 4, 1996, Pages 18~23
Fluctuation statistics of scattering strength are not only important because they impact the performance of active sonar systems, but also because they may provide insight into the major scattering process. In this article, analysis of the statistical characteristics of bottom backscattering, measured in shallow water, are presented. The slowly moving experimental sonar was operated at 30kHz to gather data over the bottom. Spatial and temporal correlation functions of the signal amplitudes were measured. The distribution function and probability of false alarm function of the detected envelope of widebeam and narrowbeam signals were measured. An attempt was made to compare the results with existing theoretical models. The result suggests that the statistical characteristics of bottom backscattering fluctuation of moving source is differ from that of fixed source.
A Speech Translation System for Hotel Reservation
The Journal of the Acoustical Society of Korea, volume 15, issue 4, 1996, Pages 24~31
In this paper, we present a speech translation system for hotel reservation, KT_STS(Korea Telecom Speech Translation System). KT-STS is a speech-to-speech translation system which translates a spoken utterance in Korean into one in Japanese. The system has been designed around the task of hotel reservation(dialogues between a Korean customer and a hotel reservation de나 in Japan). It consists of a Korean speech recognition system, a Korean-to-Japanese machine translation system and a korean speech synthesis system. The Korean speech recognition system is an HMM(Hidden Markov model)-based speaker-independent, continuous speech recognizer which can recognize about 300 word vocabularies. Bigram language model is used as a forward language model and dependency grammar is used for a backward language model. For machine translation, we use dependency grammar and direct transfer method. And Korean speech synthesizer uses the demiphones as a synthesis unit and the method of periodic waveform analysis and reallocation. KT-STS runs in nearly real time on the SPARC20 workstation with one TMS320C30 DSP board. We have achieved the word recognition rate of 94. 68% and the sentence recognition rate of 82.42% after the speech recognition tests. On Korean-to-Japanese translation tests, we achieved translation success rate of 100%. We had an international joint experiment in which our system was connected with another system developed by KDD in Japan using the leased line.
Electric Spark System as Underwater Acoustic Source - I. Pressure pulses from low electric energy -
Kim, Sung-Boo ; Kim, Sang-Han ;
The Journal of the Acoustical Society of Korea, volume 15, issue 4, 1996, Pages 32~35
The pressure pulses generated from the underwater electric spark system ranged from 0.4 to 1.6kJ are measured with the variation of source depth and range. The characteristics of pressure pulses obtained through this experiment continue to show the same electric energy and depth dependence previously reported, but two particular phenomena are observed. First, it is observed that the peak pressure of the 1st bubble pulse induced from implosion is higher than that of the initial shock wave, which is particularily apparent to high electric energy more than 10kJ previous studies. Second, it has been reported that the energy ratio (potential energy of bubble/intrinsic energy of source) has some tendency to "droop" on the low electric energy as 0.02 for 5kJ and 0.01 for 1kJ but the results of the present experiment show that it continues to have the ratio of 0.01 near 1kJ again.
Estimation of HMM parameters Using a Codeword Dependent Distance Normalization and a Distance Based codeword Weighting by Fuzzy Contribution
Choi, Hwan-Jin ; Oh, Yung-Hwan ;
The Journal of the Acoustical Society of Korea, volume 15, issue 4, 1996, Pages 36~42
In this paper, we have proposed the robust estimation of HMM parameters which is based on CDDN(codeword dependent distance normalization)and codeword weighting by distance. The proposed method has used a distance normalization based on the characteristics of a codeword dependent distribution and have computed fuzzy contributions of codeword to a input vector with a fuzzy objective function. From experimental results, we have shown the effectiveness of the proposed method in that the correction rate of the proposed method is improved 4.5% over the conventional FVQ based method. Especially, the application of distance weighting to smoothing of output probability is improved the performance of 2.5% compared to distance based codeword weighting.
A study on the Method of the Keyword Spotting Recognition in the Continuous speech using Neural Network
Yang, Jin-Woo ; Kim, Soon-Hyob ;
The Journal of the Acoustical Society of Korea, volume 15, issue 4, 1996, Pages 43~49
This research proposes a system for speaker independent Korean continuous speech recognition with 247 DDD area names using keyword spotting technique. The applied recognition algorithm is the Dynamic Programming Neural Network(DPNN) based on the integration of DP and multi-layer perceptron as model that solves time axis distortion and spectral pattern variation in the speech. To improve performance, we classify word model into keyword model and non-keyword model. We make an experiment on postprocessing procedure for the evaluation of system performance. Experiment results are as follows. The recognition rate of the isolated word is 93.45% in speaker dependent case. The recognition rate of the isolated word is 84.05% in speaker independent case. The recognition rate of simple dialogic sentence in keyword spotting experiment is 77.34% as speaker dependent, and 70.63% as speaker independent.
Optimal Wavelet Selection for AR Model Parameter Identification of Nonstationary Time-Varying Signal
Shin, D.H. ; Kim, S.H. ;
The Journal of the Acoustical Society of Korea, volume 15, issue 4, 1996, Pages 50~57
In this paper, we proposed the method of optimal wavelet selection and wavelet expansion of AR(autoregressive) parameters by selected wavelet using F-test. A cost function is introduced as a wavelet selection method. Using this cost function, wavelets (D4 to D20) are tested to the synthesized signal. With this selected wavelet, we get the wavelet coefficients of AR parameters to both synthesized signal and real speech signal. To evaluate the proposed method, this wavelet based algorithm is compared with the Kalman filering algorithm. As a results, the proposed method shows a better performance by about 5-10dB than the Kalman filter.
A Numerical Speech Recognition by Parameters Estimated from the Data on the Estimated Plane and a Neural Network
Choi, Il-Hong ; Jang, Seung-Kwan ; Cha, Tae-Hoo ; Choi, Ung-Se ; Kim, Chang-Seok ;
The Journal of the Acoustical Society of Korea, volume 15, issue 4, 1996, Pages 58~64
This paper was proposed the recognition method by using parameters which was estimated from the data on the estimated plane and a neural network. After the LPC estimated in each frame algorithm was mapped to the estimated plane by the optimum feature mapping function, we estimated the C-LPC and the maximum and minimum value and 3 divided power from the mapping data on the estimated plane. As a result of the experiment of the speech recognition that those parameters were applied to the input of a neural network, it was found that those parameters estimated from the estimated plane have the features of the original speech for a change in the time scale and that the recongnition rate by the proposed methods was 96.3 percent.
Target State Analysis Based on a Single Ping in Active Sonar
Kim, Jea-Soo ;
The Journal of the Acoustical Society of Korea, volume 15, issue 4, 1996, Pages 65~69
In this paper, the techniques for target state analysis based on a single ping in the ocean environment are proposed and discussed. The first method utilizes the relationship between range and bearing in order to determine the aspect angle of target. The second method uses the Range-Doppler Map. The former method requires the multi-channel data, while the latter uses single channel data. It is concluded, from the simulation, that the target state analysis is quite possible and the techniques mentioned should be used simultaneously to get the improved results.
A Study on the Modified Adaptive MMSE Filtering for Mixed-Noise Elimination in Image Signals
Lee, Je-Il ; Kim, Sung-Hwan ;
The Journal of the Acoustical Society of Korea, volume 15, issue 4, 1996, Pages 70~76
In the case of an image corrupted with mixed noise, conventional MMSE filter can not remove such a mixed noise properly, because the impulse moise cause a certain bias of the minimum mean-square error estimate at regions close to outliers. In this paper, we proposed the new method or removal of mixed noise by combining MMSE filtering structure with local multi-windowing method according to directions and with ranked-order method. As a result, the improvement of the image quality with the proposed was obtained between about 9.7 and 35.2 times in the sense of NMSE(normalized mean square errors) evaluation than that of MMSE filter. Also, we could obtain the enhanced image in the mixed noisy image from visual and quantitative aspect.
Equivalent Circuit Modeling of Underwater Acoustic Piezoelectric Transducer
Joh, Chee-Young ; Seo, Hee-Seon ; Lee, Jung-Min ;
The Journal of the Acoustical Society of Korea, volume 15, issue 4, 1996, Pages 77~82
In this paper an identification method is presented to obtain the equivalent electric model of a sandwitch type piezoelectric transducer. Unknown parameters related to the equivalent circuit are identified by solving a nonlinear optimization problem which can minimize an error between the experimental and analytical admittances in air. The proposed method is applied to an example transducer. The validity of equivalent circuit model is demonstrated by the comparison between the experimental measurements and analytical calculations of transmitting voltage response(TVR) and receiving voltage response(RVS).
Normalization of Spectral Magnitude and Cepstral Transformation for Compensation of Lombard Effect
Chi, Sang-Mun ; Oh, Yung-Hwan ;
The Journal of the Acoustical Society of Korea, volume 15, issue 4, 1996, Pages 83~92
This paper describes Lombard effect compensation and noise suppression so as to reduce speech recognition error in noisy environments. Lombard effect is represented by the variation of spectral envelope of energy normalized word and the variation of overall vocal intensity. The variation of spectral envelope can be compensated by linear transformation in cepstral domain. The variation of vocal intensity is canceled by spectral magnitude normalization. Spectral subtraction is use to suppress noise contamination, and band-pass filtering is used to emphasize dynamic features. To understand Lombard effect and verify the effectiveness of the proposed method, speech data are collected in simulated noisy environments. Recognition experiments were conducted with contamination by noise from automobile cabins, an exhibition hall, telephone booths in down town, crowded streets, and computer rooms. From the experiments, the effectiveness of the proposed method has been confirmed.
Robust Total Least Squares Method and its Applications to System Identifications
Kim, Jin-Young ; Choi, Seung-Ho ;
The Journal of the Acoustical Society of Korea, volume 15, issue 4, 1996, Pages 93~97
The Total Least Squares(TLS) method is an unbiased estimator for solving overdetermined sets of linear equations Ax
b when errors occur in all data. However, as well as Least Squares(LS) method it doesn't show robustness while the errors have a heavy tailed probability density function. In this paper we proposed a robust method of TLS (Robust TLS, ROTLS) based on the characteristics of TLS solution. And the ROTLS is verified by applying it to system identification problems.
An Alteration Rule of Formant Transition for Improvement of Korean Demisyllable Based Synthesis by Rule
Lee, Ki-Young ; Choi, Chang-Seok ;
The Journal of the Acoustical Society of Korea, volume 15, issue 4, 1996, Pages 98~104
This paper propose the alteraton rule to compensate a formant trasition of several connected vowels for improving an unnatural synthesized continuous speech which is concatenated by each demisyllable without coarticulated formant transition for use in dmisyllable based synthesis by rule. To fullfill each formant transition part, the database of 42 stationary vowels which are segmented from the stable part of each vowels is appended to the one of Korean demisyllables, and the resonance circuit used in formant synthesis is employed to change the formant frequency of speech signals. To evaluate the synthesied speech by this rule, we carried out the alteration rule for connected vowels of the synthesized speech based on demisyllable, and compare spectrogram and MOS tested scores with the original and the demisyllable based synthesized speech without this rule. The result shows that this proposed rule can synthesize the more natural speech.
Linear Acoustic Waves in Baffled Rocket Combustion Chambers
Yoon, Myong-Won ;
The Journal of the Acoustical Society of Korea, volume 15, issue 4, 1996, Pages 105~112
A linear acoustic analysis for baffled rocket combustion chambers has been developed. This study provides the comprehensive theoretical background for the baffle as one of the stabilizing devices in a liquid rocket propulsion system. Several specific effects of baffles are presented as mechanisms by which baffles eliminate instability. Included are longitudinalization of transverse waves inside baffle compartments, severe restriction of velocity fluctuations near the injector face, and decreased normal mode frequency of the chamber.