• Proceedings of the KIEE Conference
• /
• 2003.11b
• /
• pp.215-218
• /
• 2003

The method of vocal tract normalization has been known as a successful method for improving the accuracy of speech recognition. A frequency warping procedure based low complexity and maximum likelihood has been generally applied for vocal tract normalization. In this paper, we propose a new power spectrum warping procedure that can be improve on vocal tract normalization performance than a frequency warping procedure. A mechanism for implementing this method can be simply achieved by modifying the power spectrum of filter bank in Mel-frequency cepstrum feature(MFCC) analysis. Experimental study compared our Proposal method with the well-known frequency warping method. The results have shown that the power spectrum warping is better 50% about the recognition performance than the frequency warping.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.41 no.4
• /
• pp.103-111
• /
• 2004

The method of speaker normalization has been known as the successful method for improving the accuracy of speech recognition at speaker independent speech recognition system. A frequency warping approach is widely used method based on maximum likelihood for speaker normalization. This paper propose a new power spectrum warping approach to making improvement of speaker normalization better than a frequency warping. Th power spectrum warping uses Mel-frequency cepstrum analysis(MFCC) and is a simple mechanism to performing speaker normalization by modifying the power spectrum of Mel filter bank in MFCC. Also, this paper propose the hybrid VTN combined the Power spectrum warping and a frequency warping. Experiment of this paper did a comparative analysis about the recognition performance of the SKKU PBW DB applied each speaker normalization approach on baseline system. The experiment results have shown that a frequency warping is 2.06%, the power spectrum is 3.06%, and hybrid VTN is 4.07% word error rate reduction as of word recognition performance of baseline system.

• YAKHAK HOEJI
• /
• v.38 no.4
• /
• pp.366-371
• /
• 1994

To improve the identification power of TLC/HPTLC the in situ reflectance spectra obtained directly from plates with commercial scanner are used. The spectrum normalization should be carried out prior to comparing and searching the spectra from library for the identification of compounds. Because the reflectance does not obey the Lambert-Beer's law, there arise some problems in normalization. These problems could be solved to some extent by normalizing the spectra with regression methods. The spectra are manipulated with the regression function of a curve obtained from the correlation plot. When the parabola was used as the manipulating function, the spectra were identified with the accuracy of 97% and this result was better than that of conventionally used the point and area normalization method.

• Publications of The Korean Astronomical Society
• /
• v.21 no.2
• /
• pp.101-112
• /
• 2006

We developed a new program for automatic continuum normalization of Echelle spectrographic data. Using this algorithm, we have determined spectral continuum of almost BOES data. The first advantage of this algorithm is that we can save much time for continuum determination and normalization. The second advantage is that the result of this algorithm is very reliable for almost spectral type of spectrum. But this algorithm cannot be applied directly to the spectrum which has very strong and broad emission lines, for example Wolf-Rayet type spectrum. We implanted this algorithm to the program which was developed in the previous study. And we introduced more upgraded BOES data reduction program. This program has more convenient graphical user interface environment, so users can easily reduce BOES data. Lastly, we presented the result of study on line profile variation of magnetic Ap/Bp stars analyzed using this program.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.47 no.4
• /
• pp.112-118
• /
• 2010

This paper describes a noise suppression system based on a normalization method using a time-delay neural network and line spectrum pair having a parameter of frequency domain. First, a time-delay neural network is trained using line spectrum pair values of noisy speech signals obtained by linear prediction analysis. After trained the time-delay neural network, the proposed system enhances speech signals that are degraded by a background noise. Accordingly, the proposed time-delay neural network restores from the line spectrum pair values of noisy speech signals to the line spectrum pair values of clean speech signals. It is confirmed that this system is effective for speech signals degraded by a background noise, judging from spectral distortion measurement.

• Journal of the Korean Mathematical Society
• /
• v.42 no.1
• /
• pp.65-83
• /
• 2005

In this paper, we prove that the two well-known natural normalizations of Hamiltonian functions on the symplectic manifold ($M,\;{\omega}$) canonically relate the action spectra of different normalized Hamiltonians on arbitrary symplectic manifolds ($M,\;{\omega}$). The natural classes of normalized Hamiltonians consist of those whose mean value is zero for the closed manifold, and those which are compactly supported in IntM for the open manifold. We also study the effect of the action spectrum under the ${\pi}_1$ of Hamiltonian diffeomorphism group. This forms a foundational basis for our study of spectral invariants of the Hamiltonian diffeomorphism in [8].

• Journal of Korea Multimedia Society
• /
• v.15 no.9
• /
• pp.1102-1111
• /
• 2012

In this paper, we propose a robust watermarking method against geometric attack even though the watermarked image is partially damaged. This method consists of standard image normalization which transforms any image into a predefined standard image and embedding watermark in DCT domain of standard normalized image using spread spectrum technique. The proposed standard image normalization method has an improvement over existing image normalization method, so it is robust to partial damage and geometric attack. The watermark embedding method using spread spectrum technique also has a robustness to image losses such as blurring, sharpening and compressions. In addition, the proposed watermarking method does not need an original image to detect watermark, so it is useful to public watermarking applications. Several experimental results show that the proposed watermarking method is robust to partial damage and various attacks including geometric deformation.

• The Journal of the Acoustical Society of Korea
• /
• v.24 no.2E
• /
• pp.54-60
• /
• 2005

A new multichannel blind deconvolution algorithm is proposed for speech mixtures. It employs unidirectional filters and normalization of gradient terms in the frequency domain. The proposed algorithm is shown to be approximately nonholonomic. Thus it provides improved convergence and separation performances without whitening effect for nonstationary sources such as speech and audio signals. Simulations using real world recordings confirm superior performances over existing algorithms and its usefulness for real applications.

• The Journal of the Acoustical Society of Korea
• /
• v.3 no.1
• /
• pp.25-35
• /
• 1984

This paper analysis the Dynamic Time Warping algorithms for time normalization of speech pattern and discusses the Dynamic Programming algorithm for spoken Korean isolated digits recognition. In the DP matching, feature vectors of the reference and test pattern are consisted of first three formant frequencies extracted by power spectrum density estimation algorithm of the ARMA model. The major differences in the various DTW algorithms include the global path constrains, the local continuity constraints on the path, and the distance weighting/normalization used to give the overall minimum distance. The performance criterias to evaluate these DP algorithms are memory requirement, speed of implementation, and recognition accuracy.

• Speech Sciences
• /
• v.11 no.1
• /
• pp.7-20
• /
• 2004

In this paper, we propose a two-step noise compensation algorithm in feature extraction for achieving robust speech recognition. The proposed method frees us from requiring a priori information on noisy environments and is simple to implement. First, in frequency domain, the Harmonics-based Spectral Subtraction (HSS) is applied so that it reduces the additive background noise and makes the shape of harmonics in speech spectrum more pronounced. We then apply a judiciously weighted variance Feature Vector Normalization (FVN) to compensate for both the channel distortion and additive noise. The weighted variance FVN compensates for the variance mismatch in both the speech and the non-speech regions respectively. Representative performance evaluation using Aurora 2 database shows that the proposed method yields 27.18% relative improvement in accuracy under a multi-noise training task and 57.94% relative improvement under a clean training task.