• Phonetics and Speech Sciences
• /
• v.7 no.1
• /
• pp.3-10
• /
• 2015

In this paper, different frequency scales in cepstral feature extraction are evaluated for the text-independent speaker recognition. To this end, mel-frequency cepstral coefficients (MFCCs), linear frequency cepstral coefficients (LFCCs), and bilinear warped frequency cepstral coefficients (BWFCCs) are applied to the speaker recognition experiment. In addition, the spectro-temporal features extracted by the cepstral-time matrix (CTM) are examined as an alternative to the delta and delta-delta features. Experiments on the NIST speaker recognition evaluation (SRE) 2004 task are carried out using the Gaussian mixture model-universal background model (GMM-UBM) method and the joint factor analysis (JFA) method, both based on the ALIZE 3.0 toolkit. Experimental results using both the methods show that BWFCC with appropriate warping factor yields better performance than MFCC and LFCC. It is also shown that the feature set including the spectro-temporal information based on the CTM outperforms the conventional feature set including the delta and delta-delta features.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.16 no.7
• /
• pp.1428-1436
• /
• 2012

This paper presents the delta image composition methods using Depth-Image-Based Rendering (DIBR) for 3D stereoscopic broadcasting for the low bandwidth mobile DMB broadcasting system. With DIBR, a left and depth images are transmitted to a mobile device, which restores the right view, whose quality may be poor. This paper describes delta image composition methods for the restoration while minimizing the amount of the transmitted data.

• The KIPS Transactions:PartD
• /
• v.12D no.1 s.97
• /
• pp.159-164
• /
• 2005

In a computing environment connected pan-based computers and a server by Internet, This paper describes a language learning system evaluating the quality of a handwriting string. For the purpose of the system, this paper explains how to retrieve reference data from a database, how to evaluate the quality of a handwriting string using global and local features. The Proposed system can evaluate the qualify of a handwriting string as well as a handwriting character. The qualify can be computed in the case of different language between reference and input. Therefore, we expect that the system is very useful not only for training on handwriting but also learning a language.

• Journal of Broadcast Engineering
• /
• v.13 no.5
• /
• pp.596-601
• /
• 2008

In this paper, we propose a new scheme to generate region-of-interest (ROI) enhanced depth maps in the hybrid camera system, which is composed of a low-resolution depth camera and a high-resolution stereoscopic camera. The proposed method creates an ROI depth map for the left image by carrying out a three-dimensional (3-D) warping operation onto the depth information obtained from the depth camera. Then, we generate a background depth map for the left image by applying a stereo matching algorithm onto the left and right images captured by the stereoscopic camera. Finally, we merge the ROI map with the background one to create the final depth map. The proposed method provides higher quality depth information on ROI than the previous methods.

• The Journal of the Acoustical Society of Korea
• /
• v.24 no.3
• /
• pp.133-140
• /
• 2005

Crosstalk canceller in stereo channel audio reproduction system has the purpose to deliver desired signals exactly at the listener's ear. Generally. it has a Poor performance in low frequency bands. Frequency-warped Otters are used to provide improved performance in crosstalk canceller for these problems. However. such filters are more complex to implement than conventional filters. This paper presents an efficient method for low-order IIR approximation of frequency warped crosstalk cancellation filters using Pole-zero dewarping. The method preserves the advantages of frequency warping, but has a computational complexity that is similar to the conventional method. This Paper also presents a series of experiments that validate the method of crosstalk canceller.

• Journal of the Society of Naval Architects of Korea
• /
• v.53 no.3
• /
• pp.188-194
• /
• 2016

Accurate estimation of shear flows in thin-walled beam section is the key issue to evaluate shear stress distribution of ship hull transverse section under the shear forces acting on hull girder. It is regarded that the method using the warping functions obtained by finite element formulation is the state of the art of this field. Recently, however, IACS took effect the new version of CSR in which direct calculation process of shear flow was suggested. In the direct calculation process, shear flow of ship hull section can be obtained by the addition of determinate and indeterminate shear flows calculated respectively. So, in this paper, the shear flow evaluation codes based on the process proposed by IACS CSR and warping function based method were developed respectively. The calculated results of shear flows for the several examples of ship sections were compared with each other and considered in detail.

• Journal of the Korea Society of Computer and Information
• /
• v.15 no.6
• /
• pp.73-80
• /
• 2010

Vocabulary recognition system is providing inaccurate vocabulary and similar phoneme recognition due to reduce recognition rate. It's require method of similar phoneme recognition unrecognized and efficient feature extraction process. Therefore in this paper propose phoneme likelihood error correction improvement system using based on phoneme feature Bhattacharyya distance measurement. Phoneme likelihood is monophone training data phoneme using HMM feature extraction method, similar phoneme is induced recognition able to accurate phoneme using Bhattacharyya distance measurement. They are effective recognition rate improvement. System performance comparison as a result of recognition improve represent 1.2%, 97.91% by Euclidean distance measurement and dynamic time warping(DTW) system.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.40 no.1
• /
• pp.52-54
• /
• 2015

In this paper we propose a new background motion compensation method which can be applicable to moving object detection with a moving monocular camera. To estimate the background motion, a series of image warpings are carried out for each pair of the corresponding patches, defined by the fixed-size lattice, based on the motion information extracted from the feature points surrounded by the patches and the estimated camera motion. Experiment results proved that the proposed has approximately 50% faster in execution time and 8dB higher in PSNR comparing to a conventional method.

• The KIPS Transactions:PartB
• /
• v.12B no.4 s.100
• /
• pp.437-442
• /
• 2005

For the purpose of speaker normalization in speaker independent speech recognition systems, experiments are conducted on a method based on Gaussian mixture model(GMM). The method, which is an improvement of the previous study based on vector quantizer, consists of modeling the probability distribution of canonical feature vectors by a GMM with an appropriate number of clusters, and of estimating the warp factor of a test speaker by making use of the obtained probabilistic model. The purpose of this study is twofold: improving the existing ML based methods, and comparing the performance of what is called 'soft decision' method with that of the previous study based on vector quantizer. The effectiveness of the proposed method is investigated by recognition experiments on the TIMIT corpus. The experimental results showed that a little improvement could be obtained tv adjusting the number of clusters in GMM appropriately.

• Korean Journal of Remote Sensing
• /
• v.16 no.1
• /
• pp.99-108
• /
• 2000

The purpose of this paper is to combine digital elevation models (DEM) using SPOT satellite stereo images. After DEM extraction, a grid of longitude and latitude is generated using the results of DEM extraction. Heights at each grid location are determined from the obtained DEMs by using triangular image warping interpolation that uses the heights of the three nearest neighbors. The final heights at each grid location can then be determined by using the maximum likelihood as a fusion strategy. The input images used in this paper are two pairs of SPOT stereo images and experiments show that heights of DEM are successfully fused