• Phonetics and Speech Sciences
• /
• v.12 no.2
• /
• pp.29-37
• /
• 2020

Recently, the neural network-based deep learning algorithm has dramatically improved performance compared to the classical Gaussian mixture model based hidden Markov model (GMM-HMM) automatic speech recognition (ASR) system. In addition, researches on end-to-end (E2E) speech recognition systems integrating language modeling and decoding processes have been actively conducted to better utilize the advantages of deep learning techniques. In general, E2E ASR systems consist of multiple layers of encoder-decoder structure with attention. Therefore, E2E ASR systems require data with a large amount of speech-text paired data in order to achieve good performance. Obtaining speech-text paired data requires a lot of human labor and time, and is a high barrier to building E2E ASR system. Therefore, there are previous studies that improve the performance of E2E ASR system using relatively small amount of speech-text paired data, but most studies have been conducted by using only speech-only data or text-only data. In this study, we proposed a semi-supervised training method that enables E2E ASR system to perform well in corpus in different domains by using both speech or text only data. The proposed method works effectively by adapting to different domains, showing good performance in the target domain and not degrading much in the source domain.

• Journal of the Institute of Convergence Signal Processing
• /
• v.4 no.4
• /
• pp.30-39
• /
• 2003

In this paper, we carried out the performance evaluation of HM-Net(Hidden Markov Network) speech recognition system for Korean speech databases. We adopted to construct acoustic models using the HM-Nets modified by HMMs(Hidden Markov Models), which are widely used as the statistical modeling methods. HM-Nets are carried out the state splitting for contextual and temporal domain by PDT-SSS(Phonetic Decision Tree-based Successive State Splitting) algorithm, which is modified the original SSS algorithm. Especially it adopted the phonetic decision tree to effectively express the context information not appear in training speech data on contextual domain state splitting. In case of temporal domain state splitting, to effectively represent information of each phoneme maintenance in the state splitting is carried out, and then the optimal model network of triphone types are constructed by in the parameter. Speech recognition was performed using the one-pass Viterbi beam search algorithm with phone-pair/word-pair grammar for phoneme/word recognition, respectively and using the multi-pass search algorithm with n-gram language models for sentence recognition. The tree-structured lexicon was used in order to decrease the number of nodes by sharing the same prefixes among words. In this paper, the performance evaluation of HM-Net speech recognition system is carried out for various recognition conditions. Through the experiments, we verified that it has very superior recognition performance compared with the previous introduced recognition system.

• The Journal of the Acoustical Society of Korea
• /
• v.21 no.2
• /
• pp.199-210
• /
• 2002

In this paper, we carried out the study on speech recognition using the KM-Net topology design algorithm based on decision tree state-clustering to improve the performance of acoustic models in speech recognition. The Korean has many allophonic and grammatical rules compared to other languages, so we investigate the allophonic variations, which defined the Korean phonetics, and construct the phoneme question set for phonetic decision tree. The basic idea of the HM-Net topology design algorithm is that it has the basic structure of SSS (Successive State Splitting) algorithm and split again the states of the context-dependent acoustic models pre-constructed. That is, it have generated. the phonetic decision tree using the phoneme question sets each the state of models, and have iteratively trained the state sequence of the context-dependent acoustic models using the PDT-SSS (Phonetic Decision Tree-based SSS) algorithm. To verify the effectiveness of the above algorithm we carried out the speech recognition experiments for 452 words of center for Korean language Engineering (KLE452) and 200 sentences of air flight reservation task (YNU200). Experimental results show that the recognition accuracy has progressively improved according to the number of states variations after perform the splitting of states in the phoneme, word and continuous speech recognition experiments respectively. Through the experiments, we have got the average 71.5%, 99.2% of the phoneme, word recognition accuracy when the state number is 2,000, respectively and the average 91.6% of the continuous speech recognition accuracy when the state number is 800. Also we haute carried out the word recognition experiments using the HTK (HMM Too1kit) which is performed the state tying, compared to share the parameters of the HM-Net topology design algorithm. In word recognition experiments, the HM-Net topology design algorithm has an average of 4.0% higher recognition accuracy than the context-dependent acoustic models generated by the HTK implying the effectiveness of it.

• Journal of the Institute of Electronics Engineers of Korea SC
• /
• v.42 no.4 s.304
• /
• pp.11-18
• /
• 2005

For expressing intention the human often use body languages as well as vocal languages. Of course the gestures using arms and hands are the representative ones among the body languages. Therefore it is very important to understand the human arm motion in human-computer interaction. In this respect we present here how to estimate 3D pose of human arms by using computer vision systems. For this we first focus on the idea that the human arm motion consists of mostly revolute joint motions, and then we present an algorithm for understanding 3D motion of a revolute joint using vision systems. Next we apply it to estimating 3D pose of human arms using vision systems. The fundamental idea for this algorithm extension is that we may apply the algorithm for a revolute joint to each of the revolute joints of hmm arms one after another. In designing the algorithms we focus on seeking closed-form solutions with high accuracy because we aim at applying them to human computer interaction for ubiquitous computing and virtual reality.

• The Journal of the Acoustical Society of Korea
• /
• v.22 no.2
• /
• pp.135-144
• /
• 2003

A method for the automatic segmentation of speech signals is described. The method is dedicated to the construction of a large database for a Text-To-Speech (TTS) synthesis system. The main issue of the work involves the refinement of an initial estimation of phone boundaries which are provided by an alignment, based on a Hidden Market Model(HMM). Multi-layer perceptron (MLP) was used as a phone boundary detector. To increase the performance of segmentation, a technique which individually trains an MLP according to phonetic transition is proposed. The optimum partitioning of the entire phonetic transition space is constructed from the standpoint of minimizing the overall deviation from hand labelling positions. With single speaker stimuli, the experimental results showed that more than 95% of all phone boundaries have a boundary deviation from the reference position smaller than 20 ms, and the refinement of the boundaries reduces the root mean square error by about 25%.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.41 no.6
• /
• pp.155-164
• /
• 2004

Recently, we have remarkable developments in intelligent robot systems. The remarkable features of intelligent robot are that it can track user and is able to doface recognition, which is vital for many surveillance-based systems. The advantage of face recognition compared with other biometrics recognition is that coerciveness and contact that usually exist when we acquire characteristics do not exist in face recognition. However, the accuracy of face recognition is lower than other biometric recognition due to the decreasing in dimension from image acquisition step and various changes associated with face pose and background. There are many factors that deteriorate performance of face recognition such as thedistance from camera to the face, changes in lighting, pose change, and change of facial expression. In this paper, we implement a new sliding active camera system to prevent various pose variation that influence face recognition performance andacquired frontal face images using PCA and HMM method to improve the face recognition. This proposed face recognition algorithm can be used for intelligent surveillance system and mobile robot system.

• The Journal of the Acoustical Society of Korea
• /
• v.22 no.1
• /
• pp.42-47
• /
• 2003

This paper proposes the method to generate new test data using the sample shift of the start frame for SPRT(sequential probability ratio test) in speaker verification. The SPRT method is a effective algorithm that can reduce the test computational complexity. However, in making the decision procedure, SPRT can be executed on the assumption that the input samples are usually to be i.i.d. (Independent and Identically Distributed) samples from a probability density function (pdf), also it's not suitable method to apply for the short utterance. The proposed method can achieve SPRT regardless of the utterance length of the test data because it is method to generate the new test data through the sample shift of start frame. Also, the correlation property of data to be considered in the SPRT method can be effectively removed by employing the principal component analysis. Experimental results show that the proposed method increased the computational complexity of data for sample shift a little, but it has a good performance result more than a conventional method above the average 0.7% in EER (equal error rate).

• The Journal of the Korea institute of electronic communication sciences
• /
• v.9 no.11
• /
• pp.1221-1226
• /
• 2014

In an effort to improve the efficiency of the speech recognition, we investigate the effect of the number of phoneme clusters. For this purpose, codebooks of varied number of phoneme clusters are prepared by modified k-means clustering algorithm. The subsequent processing is fuzzy vector quantization (FVQ) and hidden Markov model (HMM) for speech recognition test. The result shows that there are two distinct regimes. For large number of phoneme clusters, the recognition performance is roughly independent of it. For small number of phoneme clusters, however, the recognition error rate increases nonlinearly as it is decreased. From numerical calculation, it is found that this nonlinear regime might be modeled by a power law function. The result also shows that about 166 phoneme clusters would be the optimal number for recognition of 300 isolated words. This amounts to roughly 3 variations per phoneme.

• Nuclear Engineering and Technology
• /
• v.54 no.11
• /
• pp.4111-4124
• /
• 2022

The control rod drive system is critical to the reactor's reliable operation. The performance of its control system and mechanical system will gradually deteriorate because of operational and environmental stresses, thus increasing the reactor's operational risk. Currently there are few researches on the aging-related degradation of the entire control rod drive system. Because it is difficult to quantify the effect of various environmental stresses and establish an accurate physical model when multiple mechanisms superimposed in the degradation process. Therefore, this paper investigates the aging-related degradation of a control rod drive system by integrating Dynamic Object-Oriented Bayesian Network and Hidden Markov Model. Uncertainties in the degradation of the control system and mechanical system are addressed by using fuzzy theory and the Hidden Markov Model respectively. A system which consists of eight control rod drive mechanisms divided into two groups is used to demonstrate the method. The aging-related degradation of the control rod drive system is analyzed by the Bayesian inference algorithm based on the accelerated life test data, and the impact of different operating schemes on the system performance is also investigated. Meanwhile, the components or units that have major impact on the system's performance are identified at different operational phases. Finally, several essential safety measures are suggested to mitigate the risk caused by the system degradation.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.16 no.1
• /
• pp.49-54
• /
• 2006

The recent fingerprint recognition system has unstable factors, such as copy of fingerprint patterns and hacking of fingerprint feature point, which mali cause significant system error. Thus, in this research, we used the fingerprint as the main recognition device and then implemented the multi-biometric recognition system in serial using the speech recognition which has been widely used recently. As a multi-biometric recognition system, once the speech is successfully recognized, the fingerprint recognition process is run. In addition, speaker-dependent DTW(Dynamic Time Warping) algorithm is used among existing speech recognition algorithms (VQ, DTW, HMM, NN) for effective real-time process while KSOM (Kohonen Self-Organizing feature Map) algorithm, which is the artificial intelligence method, is applied for the fingerprint recognition system because of its calculation amount. The experiment of multi-biometric recognition system implemented in this research showed 2 to $7\%$ lower FRR (False Rejection Ratio) than single recognition systems using each fingerprints or voice, but zero FAR (False Acceptance Ratio), which is the most important factor in the recognition system. Moreover, there is almost no difference in the recognition time(average 1.5 seconds) comparing with other existing single biometric recognition systems; therefore, it is proved that the multi-biometric recognition system implemented is more efficient security system than single recognition systems based on various experiments.