• The Journal of the Acoustical Society of Korea
• /
• v.26 no.6
• /
• pp.250-258
• /
• 2007

Current speech recognition technology s achieved high performance with the development of hardware devices, however it is insufficient for some applications where high reliability is required, such as voice control of powered wheelchairs for disabled persons. For the system which aims to operate powered wheelchairs safely by voice in real environment, we need to consider that non-voice commands such as user s coughing, breathing, and spark-like mechanical noise should be rejected and the wheelchair system need to recognize the speech commands affected by disability, which contains specific pronunciation speed and frequency. In this paper, we propose non-voice rejection method to perform voice/non-voice classification using both YIN based fundamental frequency(F0) extraction and reliability in preprocessing. We adopted a multi-template dictionary and acoustic modeling based speaker adaptation to cope with the pronunciation variation of inarticulately uttered speech. From the recognition tests conducted with the data collected in real environment, proposed YIN based fundamental extraction showed recall-precision rate of 95.1% better than that of 62% by cepstrum based method. Recognition test by a new system applied with multi-template dictionary and MAP adaptation also showed much higher accuracy of 99.5% than that of 78.6% by baseline system.

• Journal of KIISE
• /
• v.41 no.10
• /
• pp.847-858
• /
• 2014

Until now, a lot of image quality assessment techniques or tools for optimal human visual system(HVS)-awareness have been researched and SSIM(Structural SIMilarity) and its improved techniques are representative examples. However, they often cannot cope with various images and different distortion types robustly, and thus this can cause a large gap between their index values and HVS-awareness. In this paper, we conduct image quality assessment on SSIM and its variants intensively and analyze the causes of each component function's observed anomalies. Then, we propose a novel image quality assessment technique to compensate and improve such anomalies. Additionally, through extensive image assessment simulations, we show that the proposed technique can indicate HVS-awareness more robustly and consistently than SSIM and its variants for various images and different distortion types.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.14 no.6
• /
• pp.1409-1415
• /
• 2010

In this paper we proposed the watermarking technique using the markspace which is selected by tree-structure between the subbands in the wavelet domain and feature information in the spatial domain. The watermarking candidate region in the wavelet domain is obtained by the markspace selection algorithm divides the highest frequency subband to several segments and calculates theirs energy and the averages value of the total energy of the subband. Also the markspace of the spatial domain is obtained by the boundary information of a image. The final markspace is selected by the markspaces of the wavelet and spatial domain. The watermark is embedded into the selected markspace using the random addresses by LFSR. Finally the watermarking image is generated using the inverse wavelet transform. The proposed watermarking algorithm shows the robustness against the attacks such as JPEG, blurring, sharpening, and gaussian noise.

• Journal of the Institute of Electronics Engineers of Korea CI
• /
• v.40 no.3
• /
• pp.156-163
• /
• 2003

Most watermarking techniques insert watermarks into transform coefficients in the frequency domain because we can consider robust or imperceptible frequency bands against malicious attacks to remove them. However, parameterization of 3-D data is not easy because of irregular attribution of connectivity information, while 1-I) or 2-D data is regular. In this paper we propose a new watermarking scheme for 3-D polygonal mesh models in the DCT domain. After we generate triangle strips by traversing the 3-D model and transform its vertex coordinates into the DCT domain, watermark signals are inserted into mid-frequency bands of AC coefficients for robustness and imperceptibility. We demonstrate that our scheme is robust against additive random noise, the affine transformation, and geometry compression by the MPEG-4 SNHC standard.

• The Journal of the Acoustical Society of Korea
• /
• v.34 no.4
• /
• pp.316-320
• /
• 2015

In this paper, the pole filtering concept is applied to the Mel-frequency cepstral coefficient (MFCC) feature vectors in the conventional cepstral mean normalization (CMN) and cepstral mean and variance normalization (CMVN) frameworks. Additionally, performance of the cepstral mean and scale normalization (CMSN), which uses scale normalization instead of variance normalization, is evaluated in speech recognition experiments in noisy environments. Because CMN and CMVN are usually performed on a per-utterance basis, in case of short utterance, they have a problem that reliable estimation of the mean and variance is not guaranteed. However, by applying the pole filtering and scale normalization techniques to the feature normalization process, this problem can be relieved. Experimental results using Aurora 2 database (DB) show that feature normalization method combining the pole-filtering and scale normalization yields the best improvements.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.35 no.3C
• /
• pp.314-319
• /
• 2010

The chirp spread spectrum (CSS) technique that spreads the data signal over a wider frequency band via chirp signal for transmission has attracted much attention in the field of wireless communications due to capability to resist multipath fading signals. However, there has been little mathematical analysis for the performance of CSS-based communication systems in the multipath fading environments. In this paper, we study the influence of the multipath channel on the direct modulation (DM) scheme with M-ary phase shift keying (MPSK). When a chirp signal is transmitted on the Rayleigh fading channel and affected by additive white Gaussian noise (AWGN), we derive the theoretical performance. From numerical results, it is confirmed that the analytic symbol error rate (SER) agrees closely with the empirical SER.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.23 no.5
• /
• pp.41-46
• /
• 2023

It is very important to meet the maximum detection range in a radar system. In order to meet the maximum detection Range, the sensitivity of the received signal of the radar system must be high. In addition, the dynamic range should be wide in the radar signal processing board. To meet these requirements, the signal processing board must be designed to be robust against external and internal noise. In particular, a design is required to minimize the effect of noise generated by various switching circuits inside the board on the received radar signal. In this paper, we derive the requirements of the signal processor board to meet the radar system performance and describe the design to meet the derived requirements. In addition, the EMC design to minimize the influence of noise input from the outside or generated from the inside is described. Confirm the secured performance through the test of the manufactured board.

• The Journal of the Acoustical Society of Korea
• /
• v.28 no.4
• /
• pp.401-407
• /
• 2009

In this paper, we propose a novel method for the cross-correlation based double-talk detection (DTD), which employing the Gaussian Mixture Model (GMM) in the frequency domain. The proposed algorithm transforms the cross correlation coefficient used in the time domain into 16 channels in the frequency domain using the discrete fourier transform (DFT). The channels are then selected into seven feature vectors for GMM and we identify three different regions such as far-end, double-talk and near-end speech using the likelihood comparison based on those feature vectors. The presented DTD algorithm detects efficiently the double-talk regions without Voice Activity Detector which has been used in conventional cross correlation based double-talk detection. The performance of the proposed algorithm is evaluated under various conditions and yields better results compared with the conventional schemes. especially, show the robustness against detection errors resulting from the background noises or echo path change which one of the key issues in practical DTD.

• Journal of Navigation and Port Research
• /
• v.31 no.6
• /
• pp.447-454
• /
• 2007

To assess the port development and maritime traffic environment, the future traffic volume has been estimated using the number of inbound and outbound vessel for a specific port. The estimation of future traffic volume should be considered as an important factor to establish the degree of fairway congestion, the determination of fairway width and the operational role. Until now, the number of in and out vessel for the port has been only estimated mainly, but the type and size of inbound and outbound ships are different depending on the port's characteristics. So, it is difficult to estimate the future traffic volume using the change of only one item. This paper calculates the future traffic volume using the marine traffic characteristic factors as the number of coastal ship and ocean-going ship, the size of ship and the change of cargo volume per a ship etc. And it compared with the results of Artificial Neural Network(ANN) for accurate identification of nonlinear system.

• The Journal of the Acoustical Society of Korea
• /
• v.41 no.6
• /
• pp.610-620
• /
• 2022

An acoustic vector sensor can simultaneously receive vector quantities, such as particle velocity and acceleration, as well as acoustic pressure at one location, and thus it can be used as a single input multiple output receiver in underwater acoustic communication systems. On the other hand, vector signals received by a single vector sensor have different channel characteristics due to the azimuth angle between the source and receiver and the difference in propagation angle of multipath in each component, producing different communication performances. In this paper, we propose a channel parameter-based weighting method to improve the performance of an acoustic communication system using a single vector sensor. To verify the proposed method, we used communication data collected from the experiment conducted during the KOREX-17 (Korea Reverberation Experiment). For communication demodulation, block-based time reversal technique which is robust against time-varying channels were utilized. Finally, the communication results showed that the effectiveness of the channel parameter-based weighting method for the underwater communication system using a single vector sensor was verified.