Hyun-Yeol Chung

A secure watermarking for JPEG-2000

We propose a discrete wavelet transform (DWT) based watermarking method, which can be conveniently integrated in the forthcoming JPEG-2000 baseline. Conventional DWT-based watermarking techniques insert a watermark into the coefficients after the transform is completed, while the proposed method inserts a watermark into the coefficients obtained from the ongoing process of lifting for DWT. The proposed method allows us to determine selectively frequency characteristics of the coefficients where the watermark is embedded, so that the watermark cannot be easily removed or altered even when filter-banks for DWT are known. Through simulations, we show that the proposed method is more secure and more robust against various attacks than the conventional DWT-based watermarking.

Robust watermarking on polygonal meshes using distribution of vertex norms

Most watermarking techniques for 3-D mesh models have mainly focused on robustness against various attacks, such as adding noise, smoothing, simplification, re-meshing, clipping, and so on. These attacks perceptually damage the stego model itself. Unlike watermarking of other multimedia data, serious attacks for 3-D meshes includes similarity transform and vertex re-ordering. They can fatally destroy the watermark without any perceptual degradation of the stego model. In this paper, we propose a new watermarking technique for 3-D polygonal mesh model, which modifies the distribution of vertex norms according to watermark bit to be embedded. In particular, the proposed employs blind watermark detection technique, which extracts the watermark without referring to cover meshes. The simulation results show that the proposed is remarkably robust against similarity transform and vertex re-ordering.

Echo Watermarking in Sub-band Domain

Echo hiding is a method for embedding information, called watermark, into an audio signal. In general, echo hiding is processed in the time domain by convolving audio signal with echo kernel, without any consideration of the frequency characteristics. In this paper, we propose an echo hiding technique, which inserts echo into sub-band signal so as to take account into the frequency characteristics. The proposed echo hiding enables to embed high-energy echo, while minimizing the host audio quality distortion. In addition, the proposed allows increasing watermark capacity, since it is possible to embed simultaneously some watermark bits into different sub-band signals. The simulation results show that the proposed is more effective than the conventional echo hiding, in terms of watermark capacity and robustness against various attacks.

New state clustering of hidden Markov network with Korean phonological rules for speech recognition

We adopted the Korean phonological rules to state clustering of contextual domain for representing the unknown contexts and tying the model parameters of new states in state clustering of SSS (successive state splitting). We used the decision tree-based successive state splitting (DT-SSS) algorithm, which splits the state of contexts based on phonetic knowledge. The SSS algorithm proposed by Sagayama (1992) is a powerful technique, which designed topologies of tied-state HMMs automatically, but it does not generate unknown contexts adequately. In addition it has some problem in the contextual splits procedure. In this paper, speaker independent Korean isolated word and sentence recognition experiments are carried out. In word recognition experiments, this method shows an average of 6.3% higher word recognition accuracy than the conventional HMMs, and in sentence recognition experiments, it shows an average of 90.9% recognition accuracy.

A blind watermarking for 3-d dynamic mesh model using distribution of temporal wavelet coefficients

In this paper, we present a watermarking method for 3-D mesh sequences with a fixed connectivity. The main idea is to transform each coordinate of vertex with the identical connectivity index along temporal axis using wavelet transform and modify the distribution of wavelet coefficients in temporally high (or middle)-frequency frames according to watermark bit to be embedded. Due to the use of the distribution, our method can retrieve the hidden watermark without any information about original mesh sequences in the process of watermark detection. To increase the watermark capacity, all vertices are divided into groups, namely bins, using the distribution of scaling coefficients in low-frequency frames. As the vertices with the identical connectivity index over whole frames belong to one bin, their wavelet coefficients are also assigned into the same bin. Then, the watermark is embedded into each axis of the wavelet coefficients. Through simulations we show that the proposed is fairly robust against various attacks that are probably concerned in copyright protection of 3-D mesh sequences.

Noise Robust Speech Recognition Based on Parallel Model Combination Adaptation Using Frequency-Variant

The common speech recognition system displays higher recognition performance in a quiet environment, while its performance declines sharply in a real environment where there are noises. To implement a speech recognizer that is robust in different speech settings, this study suggests the method of Parallel Model Combination adaptation using frequency-variant based on environment-awareness (FV-PMC), which uses variants in frequency; acquires the environmental data for speech recognition; applies it to upgrading the speech recognition model; and promotes its performance enhancement. This FV-PMC performs the speech recognition with the recognition model which is generated as followings: i) calculating the average frequency variant in advance among the readily-classified noise groups and setting it as a threshold value; ii) recalculating the frequency variant among noise groups when speech with unknown noises are input; iii) regarding the speech higher than the threshold value of the relevant group as the speech including the noise of its group; and iv) using the speech that includes this noise group. When noises were classified with the proposed FV-PMC, the average accuracy of classification was 56%, and the results from the speech recognition experiments showed the average recognition rate of Set A was 79.05%, the rate of Set B 79.43%m, and the rate of Set C 83.37% respectively. The grand mean of recognition rate was 80.62%, which demonstrates 5.69% more improved effects than the recognition rate of 74.93% of the existing Parallel Model Combination with a clear model, meaning that the proposed method is effective.

Performance improvement of speech recognition system using microphone array

In this paper, we present some methods to improve the performance of microphone array speech recognition system based on Limabeam algorithm. For improving recognition accuracy, we proposed weighted Mahalanobis distance (WMD) based on traditional distance measure in a Gaussian classifier and is a modified method to give weights for different features in it according to their distances after the variance normalization. Experimental results showed that Limabeam adopted weighted Mahalanobis distance measure (WMD-Limabeam) improves recognition performance significantly than those by original Limabeam. In compared experiments with some other extended versions of Limabeam algorithm such as subband Limabeam and N-best parallel model for unsupervised Limabeam, we could see that the WMD-Limabeam show higher recognition accuracy. In cases of the system that adopted WMD, we obtained correct word recognition rate of 89.4% for calibrate Limabeam and 84.6% for unsupervised Limabeam, 3.0% and 5.0% higher than original Limabeam respectively. This rate also results in 9.0% higher than delay and sum algorithm.

A robust blind audio watermarking using distribution of sub-band signals

In this paper, we propose a statistical audio watermarking scheme based on DWT (Discrete Wavelet Transform). The proposed method selectively classifies high frequency band coefficients into two subsets, referring to low frequency ones. The coefficients in the subsets are modified such that one subset has bigger (or smaller) variance than the other according to the watermark bit to be embedded. As the proposed method modifies the high frequency band coefficients that have higher energy in low frequency band, it can achieve good performances both in terms of the robustness and transparency of watermark. Besides, our watermark extraction process is not only quite simple but also blind method.

Error Tolerant Melody Matching Method in Music Information Retrieval

This paper describes a music information retrieval system which uses humming as the key for retrieval. Humming is an easy way for the user to input a melody. However, there are several problems with humming that degrade the retrieval of information. One problem is a human factor. Sometimes people do not sing accurately, especially if they are inexperienced or unaccompanied. Another problem arises from signal processing. Therefore, a music information retrieval method should be sufficiently robust to surmount various humming errors and signal processing problems. A retrieval system has to extract pitch from the user’s humming. However, pitch extraction is not perfect. It often captures half or double pitches, even if the extraction algorithms take the continuity of pitch into account. Considering these problems, we propose a system that takes multiple pitch candidates into account. In addition to the frequencies of the pitch candidates, the confidence measures obtained from their powers are taken into consideration as well. We also propose the use of a query engine with three dimensions that is an extension of the conventional DP algorithm, so that multiple pitch candidates can be treated. Moreover, in the proposed algorithm, DP paths are changed dynamically to take relative spans and pitches of input and reference notes into account in order to treat split or union of notes. In an evaluation experiment, in which the performance of a conventional system was compared with that of the proposed system, better retrieval results were obtained for the latter. Finally, we implemented a GUI based music information retrieval system.

Recognition Performance Improvement of Unsupervised Limabeam Algorithm using Post Filtering Technique

Abstract- In distant-talking environments, speech recognition performance degrades significantly due to noise and reverberation. Recent work of Michael L. Selzer shows that in microphone array speech recognition, the word error rate can be significantly reduced by adapting the beamformer weights to generate a sequence of features which maximizes the likelihood of the correct hypothesis. In this approach, called Likelihood Maximizing Beamforming algorithm (Limabeam), one of the method to implement this Limabeam is an UnSupervised Limabeam(USL) that can improve recognition performance in any situation of environment. From our investigation for this USL, we could see that because the performance of optimization depends strongly on the transcription output of the first recognition step, the output become unstable and this may lead lower performance. In order to improve recognition performance of USL, some post-filter techniques can be employed to obtain more correct transcription output of the first step. In this work, as a post-filtering technique for first recognition step of USL, we propose to add a Wiener-Filter combined with Feature Weighted Malahanobis Distance to improve recognition performance. We also suggest an alternative way to implement Limabeam algorithm for Hidden Markov Network (HM-Net) speech recognizer for efficient implementation. Speech recognition experiments performed in real distant-talking environment confirm the efficacy of Limabeam algorithm in HM-Net speech recognition system and also confirm the improved performance by the proposed method.