• The Journal of the Acoustical Society of Korea
• /
• v.38 no.4
• /
• pp.433-441
• /
• 2019

In this paper, a method of estimating speech parameters for ultrasonic Doppler signals reflected from the articulatory muscles using LSTM (Long Short Term Memory) RNN (Recurrent Neural Networks) was introduced and compared with the method using MLP (Multi-Layer Perceptrons). LSTM RNN were used to estimate the Fourier transform coefficients of speech signals from the ultrasonic Doppler signals. The log energy value of the Mel frequency band and the Fourier transform coefficients, which were extracted respectively from the ultrasonic Doppler signal and the speech signal, were used as the input and reference for training LSTM RNN. The performance of LSTM RNN and MLP was evaluated and compared by experiments using test data, and the RMSE (Root Mean Squared Error) was used as a measure. The RMSE of each experiment was 0.5810 and 0.7380, respectively. The difference was about 0.1570, so that it confirmed that the performance of the method using the LSTM RNN was better.

• The Journal of the Acoustical Society of Korea
• /
• v.35 no.2
• /
• pp.134-142
• /
• 2016

In this paper, a method synthesizing speech signal using the 40 kHz ultrasonic signals reflected from the articulatory muscles was introduced and performance was evaluated. When the ultrasound signals are radiated to articulating face, the Doppler effects caused by movements of lips, jaw, and chin observed. The signals that have different frequencies from that of the transmitted signals are found in the received signals. These ADS (Acoustic-Doppler Signals) were used for estimating of the speech parameters in this study. Prior to synthesizing speech signal, a quantitative correlation analysis between ADS and speech signals was carried out on each frequency bin. According to the results, the feasibility of the ADS-based speech synthesis was validated. ADS-to-speech transformation was achieved by the joint Gaussian mixture model-based conversion rules. The experimental results from the 5 subjects showed that filter bank energy and LPC (Linear Predictive Coefficient) cepstrum coefficients are the optimal features for ADS, and speech, respectively. In the subjective evaluation where synthesized speech signals were obtained using the excitation sources extracted from original speech signals, it was confirmed that the ADS-to-speech conversion method yielded 72.2 % average recognition rates.

• Journal of Biomedical Engineering Research
• /
• v.7 no.2
• /
• pp.169-182
• /
• 1986

Pulsed ultrasonic Doppler system is a useful diagnostic instrument to measure blood-flow-velocity, velocity profile, and volume-blood-flow. This system is more powerful compare with 2-dimensional B-scan tissue image. A system has been deve- loped and ii being evaluated using TMS 32010 DSP. We use this DSP for the purpose of real-time spectrum analyzer to obtain spectrogram in singlegate pulsed Doppler system and for the serial comb filter to cancel clutter and zero crossing counter to estimate Doppler mean frequency in multigate pulsed Doppler system. The Doppler shift of the backscattered signals is sensed in a phase detector. This Doppler signal corresponds to the mean velocity over a some region in space defined by the ultrasonic beam dimensions, transmitted pulse duration, and transducer ban(iwidth. Multi- gate pulsed Doppler system enable the transcutaneous and simultaneous assessment of the velocities in a number of adjacent sample volumes as a continuous function of time. A multigate pulsed Doppler system processing the information originating from presented.

• Journal of Biomedical Engineering Research
• /
• v.7 no.2
• /
• pp.139-146
• /
• 1986

Pulsed ultrasonic Doppler system is a useful diagnostic instrument to measure blood-flow-velocity, velocity profile, and volume-blood-flow. This system is more powerful compare with 2-dimensional B-scan tissue image. A system has been deve- loped and ii being evaluated using TMS 32010 DSP. We use this DSP for the purpose of real-time spectrum analyzer to obtain spectrogram in singlegate pulsed Doppler system and for the serial comb filter to cancel clutter and zero crossing counter to estimate Doppler mean frequency in multigate pulsed Doppler system. The Doppler shift of the backscattered signals is sensed in a phase detector. This Doppler signal corresponds to the mean velocity over a some region in space defined by the ultrasonic beam dimensions, transmitted pulse duration, and transducer ban(iwidth. Multi- gate pulsed Doppler system enable the transcutaneous and simultaneous assessment of the velocities in a number of adjacent sample volumes as a continuous function of time. A multigate pulsed Doppler system processing the information originating from presented.

• The Journal of the Acoustical Society of Korea
• /
• v.35 no.1
• /
• pp.74-82
• /
• 2016

In this paper, a new automatic speech recognition (ASR) was proposed where ultrasonic doppler signals were used, instead of conventional speech signals. The proposed method has the advantages over the conventional speech/non-speech-based ASR including robustness against acoustic noises and user comfortability associated with usage of the non-contact sensor. In the method proposed herein, 40 kHz ultrasonic signal was radiated toward to the mouth and the reflected ultrasonic signals were then received. Frequency shift caused by the doppler effects was used to implement ASR. The proposed method employed multi-channel ultrasonic signals acquired from the various locations, which is different from the previous method where single channel ultrasonic signal was employed. The PCA(Principal Component Analysis) coefficients were used as the features of ASR in which hidden markov model (HMM) with left-right model was adopted. To verify the feasibility of the proposed ASR, the speech recognition experiment was carried out the 60 Korean isolated words obtained from the six speakers. Moreover, the experiment results showed that the overall word recognition rates were comparable with the conventional speech-based ASR methods and the performance of the proposed method was superior to the conventional signal channel ASR method. Especially, the average recognition rate of 90 % was maintained under the noise environments.

• The Journal of the Acoustical Society of Korea
• /
• v.40 no.2
• /
• pp.161-168
• /
• 2021

In this paper, a Silent Speech Interface (SSI) technology was proposed in which Doppler frequency shifts of the reflected signal were used to synthesize the speech signals when 40kHz ultrasonic signal was incident to speaker's mouth region. In SSI, the mapping rules from the features derived from non-speech signals to those from audible speech signals was constructed, the speech signals are synthesized from non-speech signals using the constructed mapping rules. The mapping rules were built by minimizing the overall errors between the estimated and true speech parameters in the conventional SSI methods. In the present study, the mapping rules were constructed so that the distribution of the estimated parameters is similar to that of the true parameters by using Generative Adversarial Networks (GAN). The experimental result using 60 Korean words showed that, both objectively and subjectively, the performance of the proposed method was superior to that of the conventional neural networks-based methods.

• Journal of Biosystems Engineering
• /
• v.19 no.4
• /
• pp.301-310
• /
• 1994

The feasibility of using ultrasonic-wave doppler sensors for a measurement of the actual ground speed of agricultural machines was investigated. The actual ground speed is estimated from the doppler shift frequencies of the two ultrasonic-waves transmitted to and received from a moving object. A prototype of the speed-measurement system was designed and constructed for the performance test. The measurement system showed a good performance with a flat surface at speeds lower than 3m/s. However, it was failed to receive the reflected signals from the rough and irregular soil surfaces. Further researches to solve this problem and to improve its performance are now underway.

• Proceedings of the KIEE Conference
• /
• 1988.07a
• /
• pp.709-712
• /
• 1988

Ultrasonic Doppler Diagnostic System utilizes the Doppler effect for measurement of blood velocity. The sign of the Doppler frequency shift represents blood flow direction. CW(Continuous-Wave) Doppler System uses quadrature detection and phase rotation method to produce simultaneous independent audio and velocity signals for forward and reverse blood flow direction in the time-domain, had been fabricated. But time-domain analyzing such as audio evaluation and zero- crossing detection for instantaneous and mean frequnecy measurement do not provide both an accurate and quantitative result. Therefore, it is necessary to adopt frequency-domain technique to improve system performance. In this paper, we describe a unit which is composed of CW Doppler System and real-time spectrum analyzer (installed TMS 32010 DSP Chip). This unit shows time-dependent spectrum variation and mean velocity of Blood signal.

• Journal of the Korean Institute of Telematics and Electronics
• /
• v.23 no.3
• /
• pp.389-396
• /
• 1986

A pulsed ultrasonic doppler flowmeter for mesurements of velocity profils in man is described. The device projects a beam of ultrasound in burst of 570 ns duration at 3.5 MHz. The back-scattered signals are processed to produce a signal oxrresponding to the mean velocity over a small region of the flowing stream. The observation range of 112mm is divided into 128 depth channels. The size of this sample volume determines the flowmeter sensitivity and accuracy. The device uses a quadrature detector to detect the direction of the moving target(hemoglobin). The main feature of the novel instrumnet is its simple hardware structure due to sequential signal processing.

• Journal of Biomedical Engineering Research
• /
• v.11 no.1
• /
• pp.147-156
• /
• 1990

A two-dimensional pulsed doppler system for ultrasonic blood velocity doppler signals is studied and implemented. The second-order sampling method and serial data processing procedures are utillized in the sys- tem, which eliminates the untuning problems at phase channels in the quadrature detection method as well as in the channels of parallel data processing. rho digital signal processor used in this system allows a hardware savings and flexible design options. The efficiency of the various mean frequency estimators in the second-order sampling system is examined by computer simulation as a function of the intersequence sample delay time. The temporal delay for the quadrature component is changed from $1/(4f_o){\;}to{\;}3/(4f_o){\;}and{\;}5/(4f_o)$ where to is the center frequency of the transducer, It is found that autocorrelator is the optimum frequency estimator for the second-order sampling: with !he intersequence sample delay of $1/(4f_o){\;}to{\;}3/(4f_o){\;}and{\;}5/(4f_o)$. The qualitative variation and information proportional to blood velocity in the vessel system are obtained in the VIVO experiments.