• Journal of Korea Multimedia Society
• /
• v.18 no.7
• /
• pp.834-842
• /
• 2015

We propose a method to construct composite feature vector based on discriminant analysis for face recognition. For this, we first extract the holistic- and local-features from whole face images and local images, which consist of the discriminant pixels, by using a discriminant feature extraction method. In order to utilize both advantages of holistic- and local-features, we evaluate the amount of the discriminative information in each feature and then construct a composite feature vector with only the features that contain a large amount of discriminative information. The experimental results for the FERET, CMU-PIE and Yale B databases show that the proposed composite feature vector has improvement of face recognition performance.

• Proceedings of the Acoustical Society of Korea Conference
• /
• autumn
• /
• pp.117-120
• /
• 2001

Recognition rate of Korean digit is lower than that of other words because it is composed of similar phonemes. In this paper, a new method is proposed for the improvement of recognition rate by using the phoneme boundary information. In addition, the proposed method rarely increase cost because phoneme boundary is found by using simple method. We experimented with speech data of one man and then obtained results of enhanced speech recognition rate.

• Speech Sciences
• /
• v.9 no.4
• /
• pp.253-263
• /
• 2002

In this paper, we propose new algorithm of speaker recognition which identifies the speaker using the information obtained by the intensive speech feature analysis such as pitch, intensity, duration, and formant, which are crucial parameters of individual voice, for candidates of high percentage of wrong recognition in the existing speaker recognition algorithm. For testing the power of discrimination of individual parameter, DTW (Dynamic Time Warping) is used. We newly set the range of threshold which affects the power of discrimination in speech verification such that the candidates in the new range of threshold are finally discriminated in the next stage of sound parameter analysis. In the speaker verification test by using voice DB which consists of secret words of 25 males and 25 females of 8 kHz 16 bit, the algorithm we propose shows about 1% of performance improvement to the existing algorithm.

• Proceedings of the KIEE Conference
• /
• 1998.07g
• /
• pp.2448-2450
• /
• 1998

For the exact classification of the arm motion this paper proposes EMG pattern recognition method with neural network. For this autoregressive coefficient, linear cepstrum coefficient, and adaptive cepstrum coefficient are selected for the feature parameter of EMG signal, and they are extracted from time series EMG signal. For the function recognition of the feature parameter a radial basis function network, a field of neural network is designed. For the improvement of recognition rate, a number of radial basis function network are combined in parallel, comparing with a backpropagation neural network an existing method.

• Journal of IKEEE
• /
• v.17 no.1
• /
• pp.51-56
• /
• 2013

This thesis propose a improved matching method for implementing an ORB algorithm based multi-object recognition. SURF algorithm that is well known in the object recognition algorithms is robust in object recognition. However, there is a disadvantage for real time operation because, SURF implemention requires a lot of computation. Therefore we propose a modified ORB algorithm which shows the result of almost 70% speed improvement by improving matching part to recognize multi object on real time.

• Phonetics and Speech Sciences
• /
• v.3 no.1
• /
• pp.45-50
• /
• 2011

Formant structure of speech associated with five different emotions (anger, fear, happiness, neutral, sadness) was analysed. Acoustic separability of vowels (or emotions) associated with a specific emotion (or vowel) was estimated using F-ratio. According to the results, neutral showed the highest separability of vowels followed by anger, happiness, fear, and sadness in descending order. Vowel /A/ showed the highest separability of emotions followed by /U/, /O/, /I/ and /E/ in descending order. The acoustic results were interpreted and explained in the context of previous articulatory and perceptual studies. Suggestions for the performance improvement of an automatic emotion recognition system and automatic speech recognition system were made.

• Phonetics and Speech Sciences
• /
• v.9 no.2
• /
• pp.103-110
• /
• 2017

The pole filtering concept has been successfully applied to cepstral feature normalization techniques for noise-robust speech recognition. In this paper, it is proposed to apply the pole filtering selectively only to the speech intervals, in order to further improve the recognition performance for short utterances in noisy environments. Experimental results on AURORA 2 task with clean-condition training show that the proposed selectively pole-filtered cepstral mean normalization (SPFCMN) and selectively pole-filtered cepstral mean and variance normalization (SPFCMVN) yield error rate reduction of 38.6% and 45.8%, respectively, compared to the baseline system.

• Journal of Aerospace System Engineering
• /
• v.14 no.6
• /
• pp.44-57
• /
• 2020

The ICAO AMO global recognition system will be instituted in 2024, with the aim of reducing the certification and surveillance burden on aviation authorities and approved maintenance organizations (AMOs). If the domestic AMO certification and surveillance system is internationally recognized through this system, it may facilitate the rapid development of the domestic MRO industry in South Korea. To ensure international recognition of the domestic AMO system, the AMO surveillance and regulation system must be improved. This study reviewed ICAO policies, standards, guidelines, and leading aviation authorities' regulations and systems with regard to maintenance organization certification and surveillance, and a comparative analysis with the domestic system was conducted. From this, gaps in aviation safety inspection personnel training, qualification, and surveillance were identified, and measures for improving inspection personnel training and organization certification and surveillance system maintenance were elucidated to preemptively respond to the ICAO AMO global recognition system.

• Phonetics and Speech Sciences
• /
• v.12 no.3
• /
• pp.65-71
• /
• 2020

Feature normalization is a method to reduce the effect of environmental mismatch between the training and test conditions through the normalization of statistical characteristics of acoustic feature parameters. It demonstrates excellent performance improvement in the traditional Gaussian mixture model-hidden Markov model (GMM-HMM)-based speech recognition system. However, in a deep neural network (DNN)-based speech recognition system, minimizing the effects of environmental mismatch does not necessarily lead to the best performance improvement. In this paper, we attribute the cause of this phenomenon to information loss due to excessive feature normalization. We investigate whether there is a feature normalization method that maximizes the speech recognition performance by properly reducing the impact of environmental mismatch, while preserving useful information for training acoustic models. To this end, we introduce the mean and exponentiated variance normalization (MEVN), which is a compromise between the mean normalization (MN) and the mean and variance normalization (MVN), and compare the performance of DNN-based speech recognition system in noisy and reverberant environments according to the degree of variance normalization. Experimental results reveal that a slight performance improvement is obtained with the MEVN over the MN and the MVN, depending on the degree of variance normalization.

• IEMEK Journal of Embedded Systems and Applications
• /
• v.8 no.4
• /
• pp.185-194
• /
• 2013

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.