• The Journal of the Acoustical Society of Korea
• /
• v.11 no.1
• /
• pp.35-41
• /
• 1992

A speaker identification scheme using the speaker-based VQ codecook of a sustained vowel is proposed and tested. With the pitch synchronous LPC vector of the sustained vowel /i/ as a feature vector, a VQ codebook size of 4 was found to be suitable to characterize each speaker's feature space. For 40 normal speakers (20 males, 20 females), we achieved the correct identification rate of 99.4% with a training data set, and 89.4% with a test data set with speech samples of only 50 pitch periods.

• Journal of the Korean Institute of Telematics and Electronics S
• /
• v.34S no.4
• /
• pp.57-65
• /
• 1997

The purpose of this paper is to propose the HMM (hidden markov model) based on multi-observation sequence for the isolated word recognition. The proosed model generates the codebook of MSVQ by dividing each word into several sections followed by dividing training data into several sections. Then, we are to obtain the sequential value of multi-observation per each section by weighting the vectors of distance form lower values to higher ones. Thereafter, this the sequential with high probability value while in recognition. 146 DDD area names are selected as the vocabularies for the target recognition, and 10LPC cepstrum coefficients are used as the feature parameters. Besides the speech recognition experiments by way of the proposed model, for the comparison with it, the experiments by DP, MSVQ, and genral HMM are made with the same data under the same condition. The experiment results have shown that HMM based on multi-observation sequence proposed in this paper is proved superior to any other methods such as the ones using DP, MSVQ and general HMM models in recognition rate and time.

• Journal of IKEEE
• /
• v.13 no.2
• /
• pp.232-240
• /
• 2009

This paper presents a robust vehicle detection and tracking algorithm for supervision of illegal parking. The proposed algorithm is composed of four parts. First, a vehicle detection algorithm is proposed using the improved codebook object detection algorithm to segment moving vehicles from the input sequence. Second, a preprocessing technique using the geometric characteristics of vehicles is employed to exclude non-vehicle objects. Then, the detected vehicles are tracked by an object tracker which incorporates histogram tracking method with Kalman filter. To make the tracking results more accurate, histogram tracking results are used as measurement data for Kalman filter. Finally, Real Stop Counter (RSC) is introduced for trustworthy and accurate performance of the stopped vehicle detection. Experimental results show that the proposed algorithm can track multiple vehicles simultaneously and detect stopped vehicles successfully in the complicated street environment.

• The Journal of the Acoustical Society of Korea
• /
• v.15 no.6
• /
• pp.5-11
• /
• 1996

This paper is the study for recognizing single vowels of speaker-independent, and we suppose a method of speech recognition using VQ(Vector Quantization)/NN(Neural Network). This method makes a VQ codebook, which is used for obtaining the observation sequence, and then claculates the probability value by comparing each codeword with the data, finally uses these probability values for the input value of the neural network. Korean signle vowels are selected for our recognition experiment, and ten male speakers pronounced eight single vowels ten times. We compare the performance of our method with those of fuzzy VQ/HMM and conventional VQ/NN According to the experiment result, the recognition rate by VQ/NN is 92.3%, by VQ/HMM using fuzzy is 93.8% and by VQ/NN using fuzzy is 95.7%. Therefore, it is shown that recognition rate of speech recognition by fuzzy VQ/NN is better than those of fuzzy VQ/HMM and conventional VQ/HMM because of its excellent learning ability.

• Journal of Satellite, Information and Communications
• /
• v.11 no.3
• /
• pp.133-137
• /
• 2016

Millimeter wave wireless communication systems, especially those targeting indoor high rate data transfer, have a strong requirement for high quality wireless link. Unfortunately, in this frequency band, the electromagnetic wave has to sustain the high propagation loss caused by the smaller wavelengths. In this scenario, beamforming technique, which enhances the link quality by focusing the radiation power on a direction, becomes one of the most important techniques in millimeter wave band wireless communication. In recent year, there been conducted many research on beamforming to improve the performance of wireless system. In this paper, we evaluate the performance of a simplified codebook-based beamforming scheme which is based on multiple-procedure and three-state beam selection. The simplified scheme significantly reduces beamforming setup time, comparing to the exhaustive searching, two-level searching adopted in IEEE 802.15.3c standard, and also conventional multi-level scheme.

• Journal of the Institute of Electronics Engineers of Korea TC
• /
• v.48 no.1
• /
• pp.70-76
• /
• 2011

LTE Re1-10 aims at peak. data rates of 1Gbits/s for the downlink and 500 Mbits/s for the uplink, which can be accomplished by not only wide spectrum but also advanced MIMO techniques such as precoded MIMO and cooperative relays. Considering some relays can have more direct signal paths than mobile stations do, LoS components are examined to build more efficient codebooks for Rician channels. The proposed codebooks perform better than the existing LTE codebooks as the criterium of LoS, K-factor increases. Conserving the advantages and max-min chordal distance of the existing LTE codebooks, the proposed ones also maximize the minimum chordal distances between codewords over Rician fading channels. Link-level simulation with LTE system parameters confirm the performance improvements as the value of K increases.

• Journal of the Korean Society for information Management
• /
• v.38 no.4
• /
• pp.153-171
• /
• 2021

This study suggested a method of utilizing METS based on DDI metadata to manage, preserve, and service datasets. DDI is a standard for statistical data processing, and there are currently two versions of DDI Codebook (DDI-C) and DDI Lifecycle (DDI-L). In this study, the main elements of DDI-C were mainly used. First the structures and elements of METS and DDI-C were first analyzed. And the mapping of the major elements of METS and DDI-C. The standard was finally taken as METS, the format to express it. Since METS and DDI-C do not show a perfect 1:1 mapping, the DDI-C element that best matches each element of the standard METS was selected. As a result, a new dataset management transmission standard METS using DDI-C metadata elements was designed and presented.

• Proceedings of the IEEK Conference
• /
• 2001.06c
• /
• pp.9-12
• /
• 2001

Learning vector quantization (LVQ) is a supervised learning technique that uses class information to move the vector quantizer slightly, so as to improve the quality of the classifier decision regions. In this paper we propose a selection method of initial codebook vectors for a teaming vector quantization (LVQ3) using support vector machines (SVM). The method is experimented with artificial and real design data sets and compared with conventional methods of the condensed nearest neighbor (CNN) and its modifications (mCNN). From the experiments, it is discovered that the proposed method produces higher performance than the conventional ones and then it could be used efficiently for designing nonparametric classifiers.

• Proceedings of the IEEK Conference
• /
• 2000.06d
• /
• pp.98-101
• /
• 2000

On CELP type Vocoders G.723.1 6.3kbps/5.3kbps Dual Rate Speech Codec, which is developed for Internet Phone and videoconferencing, uses VAD(Voice Activity Detection)/CNG (Comfort Noise Generator) in order to reduce the bit rate in a silence period. In order to reduce the bit rate effectively in this paper, we first set the boundary condition of the energy threshold to prevent the consumption of unnecessary processing time, and use three decision rules to detect an active frame by energy, pitch gain and LSP distance. To evaluate the performance of the proposed algorithm we use silence-inserted speech data with 0, 5, 10, 20dB of SNR. As a result when SNR is over 5dB, the bit rate is reduced up to about 40% without speech degradation and the processing time is additionally decreased.

• MALSORI
• /
• no.48
• /
• pp.93-105
• /
• 2003

Since telephone channel has bandlimited frequency characteristics, speech signal over the telephone channel shows degraded speech quality. In this paper, we propose an algorithm using neural network to reconstruct wideband speech from its narrowband version. Although single neural network is a good tool for direct mapping, it has difficulty in training for vast and complicated data. To alleviate this problem, we modularize the neural networks based on appropriate clustering of the acoustic space. We also introduce fuzzy computing to compensate for probable misclassification at the cluster boundaries. According to our simulation, the proposed algorithm showed improved performance over the single neural network and conventional codebook mapping method in both objective and subjective evaluations.