• Proceedings of the Acoustical Society of Korea Conference
• /
• spring
• /
• pp.65-69
• /
• 1999

합성단위, 합성기, 합성방식 등에 따라 여러 가지 다양한 음성합성시스템이 있으나 순수한 법칙합성 시스템이 아니고 기본 합성단위를 연결하여 합성음을 발생시키는 연결합성 시스템은 연결단위사이의 매끄러운 합성계수의 변화를 구현하지 못해 자연감이 떨어지는 실정이다. 자연음에 존재하는 운율법칙을 정확히 구현하면 합성음의 자연감을 높일 수 있으나 존재하는 모든 운율법칙을 추출하기 위해서는 방대한 분량의 언어자료 구축이 필요하다. 일반 의미 문장으로부터 운율법칙을 추출하는 것이 바람직하겠으나, 모든 운율 현상이 포함된 언어자료는 그 문장 수가 극히 방대하여 처리하기 힘들기 때문에 가능하면 문장 수를 줄이면서 다양한 운율 현상을 포함하는 문장 군을 구축하는 것이 중요하다. 본 논문에서는 음성학적으로 균형 잡힌 고립단어 412 단어를 기반으로 의미문장들을 만들었다. 이들 단어를 각 그룹으로 구분하여 각 그룹에서 추출한 단어들을 조합시켜 의미 문장을 만들도록 하였다. 의미 문장을 만들기 위해 단어 목록에 없는 단어를 첨가하였다. 단어의 문장 내에서의 상대위치에 따른 운율 변화를 살펴보기위해 각 문장의 변형을 만들어 언어자료에 포함시켰다. 자연감을 높이기 위해 구축된 언어자료를 바탕으로 음성데이타베이스를 작성하여 운율분석을 통해 신경망을 훈련시키기 위한 목표패턴을 작성하였다 문장의 음소열을 입력으로 하고 특정음소의 운율정보를 발생시키는 신경망을 구성하여 언어자료를 기반으로 작성한 목표패턴을 이용해 신경망을 훈련시켰다. 신경망의 입력패턴은 문장의 음소열 중 11개 음소열로 구성된다. 이 중 가운데 음소의 운율정보가 출력으로 나타난다. 분절요인에 의한 영향을 고려해주기 위해 전후 5음소를 동시에 입력시키고 문장내에서의 구문론적인 영향을 고려해주기 위해 해당 음소의 문장내에서의 위치, 운율구에 관한 정보등을 신경망의 입력 패턴으로 구성하였다. 특정화자로 하여금 언어자료를 발성하게 한 음성시료의 운율정보를 추출하여 신경망을 훈련시킨 결과 자연음의 운율과 유사한 합성음의 운율을 발생시켰다.

• The Journal of the Acoustical Society of Korea
• /
• v.14 no.5
• /
• pp.74-82
• /
• 1995

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 $6\%$ in the speaker dependent, and $80.5\%$ in the speaker independent recognition test.

• The Journal of the Acoustical Society of Korea
• /
• v.20 no.3
• /
• pp.56-62
• /
• 2001

In this paper, we adopt a missing data theory to speech recognition. It can be used in order to maintain high performance of speech recognizer when the missing data occurs. In general, hidden Markov model (HMM) is used as a stochastic classifier for speech recognition task. Acoustic events are represented by continuous probability density function in continuous density HMM(CDHMM). The missing data theory has an advantage that can be easily applicable to this CDHMM. A marginalization method is used for processing missing data because it has small complexity and is easy to apply to automatic speech recognition (ASR). Also, a spectral subtraction is used for detecting missing data. If the difference between the energy of speech and that of background noise is below given threshold value, we determine that missing has occurred. We propose a new method that examines the reliability of detected missing data using voicing probability. The voicing probability is used to find voiced frames. It is used to process the missing data in voiced region that has more redundant information than consonants. The experimental results showed that our method improves performance than baseline system that uses spectral subtraction method only. In 452 words isolated word recognition experiment, the proposed method using the voicing probability reduced the average word error rate by 12％ in a typical noise situation.

• The Journal of the Acoustical Society of Korea
• /
• v.23 no.5
• /
• pp.420-427
• /
• 2004

This paper presents real time implementation of 4kbps EHSX (Enhanced Harmonic Stochastic Excitation) speech coder that combines the harmonic vector excitation coding with time-separated transition coding. The harmonic vector excitation coding uses the harmonic excitation coding for voiced frames and used the vector excitation coding with the structure of analysis-by-synthesis for unvoiced frames, respectively. For transition frames mixed with voiced and unvoiced signal, we use the time-separated transition coding. In this paper. we present the optimization methods of implementation speech coder on the EMS320C6701/sup (R)/ DSP. To reduce the complex for real-time implementation. we perform the optimization method in algorithm by replacing the complex sinusoidal synthesis method with IFFT. and we apply fully pipelines hand assembly coding after converting it from floating source to fixed source. To generate a more efficient code. we also make use or the available EMS320C6701/sup (R)/ resources such as Fastest67x library and memory organization.

• The Journal of the Acoustical Society of Korea
• /
• v.15 no.5
• /
• pp.21-29
• /
• 1996

Industrial equipment, such as power plant, is required to operate reliably, continuously and economically under rather severe conditions of temperature, stress, and enbironment. To test structural integrity and fitness, ultrasonic nondestructive testing is used because of effectiveness and simplicity. In this paper, wavelet transform based least mean square(LMS) algorithm is applied to reduce the influence of the interference occurring between randomly positioned small scatters. The RUN test is performed to check the nonstationarity of the speckle noise signal. The performance of this new approach is compared with that of the time domain LMS algorithm by means of condition numbers, signal-to-noise ratio and 3-D image. As a result, the wavelet transform based LMS algorithm shows better performance than the time domain LMS algorithm in this experiment.

• The Journal of the Acoustical Society of Korea
• /
• v.16 no.6
• /
• pp.94-99
• /
• 1997

This paper describes a technique of probabilistic spectral subtraction which uses the knowledge of both noise and speech so as to reduce automatic speech recognition errors in noisy environments. Spectral subtraction method estimates a noise prototype in non-speech intervals and the spectrum of clean speech is obtained from the spectrum of noisy speech by subtracting this noise prototype. Thus noise can not be suppressed effectively using a single noise prototype in case the characteristics of the noise prototype are different from those of the noise contained in input noisy speech. To modify such a drawback, multiple noise prototypes are used in probabilistic subtraction method. In this paper, the probabilistic characteristics of noise and the knowledge of speech which is embedded in hidden Markov models trained in clean environments are used to suppress noise. Futhermore, dynamic feature parameters are considered as well as static feature parameters for effective noise suppression. The proposed method reduced error rates in the recognition of 50 Korean words. The recognition rate was 86.25% with the probabilistic subtraction, 72.75% without any noise suppression method and 80.25% with spectral subtraction at SNR(Signal-to-Noise Ratio) 10 dB.

• The Journal of the Acoustical Society of Korea
• /
• v.35 no.5
• /
• pp.340-348
• /
• 2016

Ray-based model for the calculation of the ocean surface-generated ambient noise coherence function has the form of double integral with respect to a range and a bearing angle. While the theoretical consideration about its numerical implementations was partly given in the past work of authors, the numerical results on the ocean environment have not been presented yet. In this paper, we perform numerical experiments for shallow and deep water environments. It is shown that the coherence function depends on the ocean sediment sound speed, and is more sensitive to the ocean sediment sound speed in the shallow water than in the deep water. Similar trend is also observed for varying the orientation of hydrophone pair. In addition, a post-processing technique is proposed in order to plot the noise intensity for the noise receiving angle. This procedure will supplement the weakness of the ray-based model about the output data type compared to the semi-analytic model of Harrison.

• The Journal of the Acoustical Society of Korea
• /
• v.37 no.4
• /
• pp.215-222
• /
• 2018

This paper reports the development and performance evaluation of a backend system for real-time IVUS (Intravascular Ultrasound) imaging. The developed backend system was designed to minimize the amount of logic and memory usage by means of efficient LUTs (Look-up Tables), and it was implemented in a single FPGA (Field Programmable Gate Array) without using external memory. This makes it possible to implement the backend system that is less expensive, smaller, and lighter. The accuracy of the backend system implemented was evaluated by comparing the output of the FPGA with the result computed using a MATLAB program implemented in the same way as the VHDL (VHSIC Hardware Description Language) code. Based on the result of ex-vivo experiment using rabbit artery, the developed backend system was found to be suitable for real-time intravascular ultrasound imaging.

• The Journal of the Acoustical Society of Korea
• /
• v.11 no.3
• /
• pp.53-60
• /
• 1992

Many adaptive beamforming methods have been studied for interference cancellation and speech signal enhancement in telephone conference and auditorium. Main aspect of adaptive beamforming methods for speech signal processing is different from radar, sonar and seismic signal processing because desire output signal should be apt to the human ear. Considering that phase of speech is quite insensible to the human ear, Sondhi proposed a nonlinear constrained optimization technique whose constraint was on the magnitude transfer function from the source to the output. In real environment the phase response of the speech signal affects the human auditorium system. So it is desirable to design linear phase system. In this paper, linear phase beamformer is proposed and sample processing algorithm is also proposed for real time consideration Simulation results show that the proposed algorithm yields more consistent beam patterns and deep nulls to the noise direction than Sondhi's.

• The Journal of the Acoustical Society of Korea
• /
• v.37 no.1
• /
• pp.46-52
• /
• 2018

The piezoelectric single crystals used in piezoelectric transformers have a problem that power transfer capacity is comparatively low due to their high input impedance. In this study, we suggest a method to improve the power transfer capacity by reducing the high input impedance of the piezoelectric single crystal vibrator by connecting a capacitance increasing circuit to the electrical terminals of the piezoelectric single crystal vibrator where the circuit is a GIC (Generalized Impedance Converter) circuit using operational amplifiers. The result of measuring driving characteristics after applying the designed capacitance increasing circuit to the $128^{\circ}$ rotated Y-cut $LiNbO_3$ crystal vibrator confirmed that the input impedance decreased by 25 %, electromechanical coupling factor increased by 30 %, and the power transfer capacity increased by about 17 to 30 times in voltage conversion characteristics.