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 14, Issue 6 - Dec 1995
Volume 14, Issue 5 - Oct 1995
Volume 14, Issue 4 - Aug 1995
Volume 14, Issue 3 - Jun 1995
Volume 14, Issue 2 - Apr 1995
Volume 14, Issue 1 - Feb 1995
Volume 14, Issue 2E - 00 1995
Volume 14, Issue 1E - 00 1995
Selecting the target year
The Application of an HMM-based Clustering Method to Speaker Independent Word Recognition
Lim, H. ; Park, S.-Y. ; Park, M.-W. ;
The Journal of the Acoustical Society of Korea, volume 14, issue 5, 1995, Pages 5~10
In this paper we present a clustering procedure based on the use of HMM in order to get multiple statistical models which can well absorb the variants of each speaker with different ways of saying words. The HMM-clustered models obtained from the developed technique are applied to the speaker independent isolated word recognition. The HMM clustering method splits off all observation sequences with poor likelihood scores which fall below threshold from the training set and create a new model out of the observation sequences in the new cluster. Clustering is iterated by classifying each observation sequence as belonging to the cluster whose model has the maximum likelihood score. If any clutter has changed from the previous iteration the model in that cluster is reestimated by using the Baum-Welch reestimation procedure. Therefore, this method is more efficient than the conventional template-based clustering technique due to the integration capability of the clustering procedure and the parameter estimation. Experimental data show that the HMM-based clustering procedure leads to
performance improvements over the conventional template-based clustering method and
improvements over the single HMM method for the case of recognition of the isolated korean digits.
Measurement of Tire Structural Vibration Noise Using Spatial Transformation of Sound Field Technique
Kim, Byoung-Sam ;
The Journal of the Acoustical Society of Korea, volume 14, issue 5, 1995, Pages 11~19
The Interaction between tire and road is responsible for the excited vibration of the tire, and It is also important for the sound radiation. In this paper. measurement of tire structural vibration noise from a chassis dynamometer using Spatial Transformation of Sound Field(STSF) technique is studied. STSF involving a scan that uses an array of transducers over a planar surface close to the source is under investigation. From cross spectra measurement during the scan, a principal component representing the sound field is extracted. Any power descriptor of the near field can then be investigated by means of near-field acoustic holography, while the distant field can be determined by application of Helmholtz integral equation. The results of the measurement were used to obtain the radiation sound pattern from the center line of the tire, and to locate the radiation sound generating regions in the vicinity of the tire.
A Study on Performance Comparison of Bussgang-type Adaptive Blind Algorithms
Kim, Hyoung-Seok ; Kang, Hyun-Cheol ; Byun, Youn-Shik ;
The Journal of the Acoustical Society of Korea, volume 14, issue 5, 1995, Pages 20~28
This paper studied adaptive blind equalizer which belong to Bussgang type. It is well known that blind equalizer performs equalization without using a training sequence. Especially, this paper concentrated on real time processing of them. The channel characteristic was obtained from measurements taken in a real urban multipath environment. A T/2 fractionally-spaced equalizer was used at the receiving end. Our computer simulations demonstrated that Stop and Go, Benveniste-Goursat, and optimal Bussgang algorithms have relatively low MSE property. CMA shows faster convergence property than any other of Bussgang type algorithm.
Determination of the Nonlinear Parameters of Stiffness and Force Factor of the Loudspeaker
Doo, Se-Jin ; Sung, Koeng-Mo ;
The Journal of the Acoustical Society of Korea, volume 14, issue 5, 1995, Pages 29~35
Nonlinear distortion arising from the nonlinear movement of the loudspeaker diaphragm degradates the tone quality. The distortion is, in low frequency range, mainly caused by nonlinear characteristics of the suspension stiffness and the force factor. In this paper, the nonlinear suspension stiffness and the nonlinear force factor are modeled to the quadratic functions and a method is proposed to determine their coefficients. An additional mass to the diaphragm moved the quiescent point of the diaphragm and uncoupled the stiffness and the force factor. This made it possible to deter mine the coefficients of the nonlinear suspension stiffness by measuring the resonance frequencies at several quiescent points. The coefficients of the nonlinear force factor are then determined by fitting the curve which is calculated from the waveforms of input voltage and input current, and the displacement of the diaphragm at resonance frequency.
Acoustic Field Analysis of Ultrasonic Focusing Transducer by Using Finite Element. Method and Hybrid Type Infinite Element Method
Park, Soon-Jong ; Yoon, Jong-Rak ; Ha, Kang-Lyeol ; Kim, Chun-Duck ;
The Journal of the Acoustical Society of Korea, volume 14, issue 5, 1995, Pages 36~43
This paper presents the lousing characteristics and the time. response of ultrasonic focusing transducer which is a coupled system with an electromechanical and an acoustical component. The Finite Element Method and the Hybrid Type Infinite Element Method are applied for the analysis. The position of the focal points and the resolutions is obtained from the loosing characteristics and the time response. It is found that the transducer with the damper, which stabilizes the displacement of the radiation surface, gives a better resolution. In conclusion, the results could be applied to the design and the performance analysis of the ultrasonic focusing transducer.
On the Development of a Large-Vocabulary Continuous Speech Recognition System for the Korean Language
Choi, In-Jeong ; Kwon, Oh-Wook ; Park, Jong-Ryeal ; Park, Yong-Kyu ; Kim, Do-Yeong ; Jeong, Ho-Young ; Un, Chong-Kwan ;
The Journal of the Acoustical Society of Korea, volume 14, issue 5, 1995, Pages 44~50
This paper describes a large-vocabulary continuous speech recognition system using continuous hidden Markov models for the Korean language. To improve the performance of the system, we study on the selection of speech modeling units, inter-word modeling, search algorithm, and grammars. We used triphones as basic speech modeling units, generalized triphones and function word-dependent phones are used to improve the trainability of speech units and to reduce errors in function words. Silence between words is optionally inserted by using a silence model and a null transition. Word pair grammar and bigram model based oil word classes are used. Also we implement a search algorithm to find N-best candidate sentences. A postprocessor reorders the N-best sentences using word triple grammar, selects the most likely sentence as the final recognition result, and finally corrects trivial errors related with postpositions. In recognition tests using a 3,000-word continuous speech database, the system attained
word recognition accuracy and
sentence recognition accuracy using word triple grammar in postprocessing.
Performance Improvement of Speech Recognizer in Noisy Environments Based on Auditory Modeling
Jung, Ho-Young ; Kim, Do-Yeong ; Un, Chong-Kwan ; Lee, Soo-Young ;
The Journal of the Acoustical Society of Korea, volume 14, issue 5, 1995, Pages 51~57
In this paper, we study a noise-robust feature extraction method of speech signal based on auditory modeling. The auditory model consists of a basilar membrane, a hair cell model and spectrum output stage. Basilar membrane model describes a response characteristic of membrane according to vibration in speech wave, and is represented as a band-pass filter bank. Hair cell model describes a neural transduction according to displacements of the basilar membrane. It responds adaptively to relative values of input and plays an important role for noise-robustness. Spectrum output stage constructs a mean rate spectrum using the average firing rate of each channel. And we extract feature vectors using a mean rate spectrum. Simulation results show that when auditory-based feature extraction is used, the speech recognition performance in noisy environments is improved compared to other feature extraction methods.
An Investigation of Self-Radiation Impedance of a Square Piston using an Integral Equation in the Rigid Infinite Baffle
Lee, Jong-Kil ; Seo, In-Chang ;
The Journal of the Acoustical Society of Korea, volume 14, issue 5, 1995, Pages 58~62
Integral equations of self-radiation impedance of a rectangular piston in a rigid infinite baffle are derived using by polar coordinate. The self-radiation impedance is separated by two parts ; self-radiation resistance and self-radiation reactance. Derived integral equations are simulated by numerical method. Based on the numerical results, self-radiation impedance can be obtained in the low and high frequency ranges without any limited conditions.
Design of the DSP for the FM Sound Synthesis
Kwon, Min-Do ; Jang, Ho-Keun ; Kim, Jae-Yong ; Park, Ju-Sung ; Kim, Hyung-Soon ; Yun, Pyung-Woo ; Baek, Kwang-Ryul ; Im, Chang-Hun ;
The Journal of the Acoustical Society of Korea, volume 14, issue 5, 1995, Pages 63~73
The conventional acoustic sounds can be synthesized by Frequency Modulation which includes the variation of frequency, amplitude, and modulation index. In this paper the number of variable synthesis parameters are limited to easily implement the existing two carrier FM algorithm by hardware. The DSP(Digital Signal Processor), which is able to carry out the modified algorithm and synthesize 16 sounds at a time, is designed with
standard sells. The DSP which can synthesize 2 sounds at a time is implemented by ASIC emulator to examine the sound quality of the designed DSP. Through the objective and subjective estimation, it is confirmed that the sounds of many instruments from the implemented DSP are very closed to their real sound. Finally the designed DSP is layouted and simulated by VLSI desgn tool. According to the simulation, the designed DSP has the sufficiently fast speed for synthesizing 16 sounds at a time.
A Study on the Voice Dialing using HMM and Post Processing of the Connected Digits
Yang, Jin-Woo ; Kim, Soon-Hyob ;
The Journal of the Acoustical Society of Korea, volume 14, issue 5, 1995, Pages 74~82
This paper is study on the voice dialing using HMM and post processing of the connected digits. HMM algorithm is widely used in the speech recognition with a good result. But, the maximum likelihood estimation of HMM(Hidden Markov Model) training in the speech recognition does not lead to values which maximize recognition rate. To solve the problem, we applied the post processing to segmental K-means procedure are in the recognition experiment. Korea connected digits are influenced by the prolongation more than English connected digits. To decrease the segmentation error in the level building algorithm some word models which can be produced by the prolongation are added. Some rules for the added models are applied to the recognition result and it is updated. The recognition system was implemented with DSP board having a TMS320C30 processor and IBM PC. The reference patterns were made by 3 male speakers in the noisy laboratory. The recognition experiment was performed for 21 sort of telephone number, 252 data. The recognition rate was
in the speaker dependent, and
in the speaker independent recognition test.
An Identification Method for Complex-Valued Material Properties of Piezoelectric Ceramics
Joh, Chee-Young ; Seo, Hee-Seon ; Kim, Dae-Hwan ;
The Journal of the Acoustical Society of Korea, volume 14, issue 5, 1995, Pages 83~88
The common practice for the identification of piezoelectric properties is based on the use of immittance of a resonator with a certain geometry and poling direction. In this paper, a new method is suggested to identify the complex-valued piezoelectric material constants. This method Is based on the minimization of differences between the analytical immittance and the experimental measurement of resonator. Non-linear minimization problems are formulated to find out the unknown properties relevant to the resonators. The immittance data used for identification are measured at a number of frequencies which cover the vicinity of resonance frequency and the low frequency region. To illustrate the proposed technique, the complex-valued coefficients are identified for a typical PZT4 ceramic composition.
A New Speech Waveform Coding Based on the Nonuniform Sampling Method with Separated to High-Low Band
Bae, Myung-Jin ; Lee, Joo-Hun ; Im, Sung-Bin ; Lee, Won-Cheol ;
The Journal of the Acoustical Society of Korea, volume 14, issue 5, 1995, Pages 89~93
To reduce the redundancy within samples that resulted from uniform sampling method, nonuniform sampling or nonredundant-sample coding methods can be considered. However, it is well known that when conventional nonuniform sampling methods are applied directly to speech signal, the required amount of data is comparable to or mure than that by uniform sampling method like PCM. To overcome this problem, a new nonuniform sampling method is proposed, in which nonuniform sampling is applied to the low-pass filtered speech signal and higher band is compensated by 8 colored Gaussian random noise with various noise levels. By this method, speech signal waveform can be encoded by 1.8 times larger compression ratio than the conventional nonuniform sampling method.
Hoarse Speech Analysis Using Dissymmetric Four-Mass Model of Vocal Cords
Jiang, Gan-Yi ; Chen, Hui-Fang ; Choi, Tae-Young ;
The Journal of the Acoustical Society of Korea, volume 14, issue 5, 1995, Pages 94~101
In this paper, a new vocal cords model, called a four-mass model, is proposed for a hoarse speech mechanism. Pathological changes of vocal cords cause hoarse speech and glottal waveform reflects motion states of vocal cords. From these facts, we assumed that the morbid vocal cords be dissymmetric and take the four-mass type. The glottal waveforms and the model parameters of normal and hoarse speech signals are analyzed, and some relations bet ween the model parameters and the hoarse pathology are discussed. Experimental results show that the new research method of hoarse speech can reveal relations between the acoustic features of hoarse speech and the hoarse pathology, and be used to diagnose laryngeal diseases and to improve tone quality of hoarse speech.