• Proceedings of the IEEK Conference
• /
• 2000.09a
• /
• pp.935-938
• /
• 2000

본 논문에서는 음성 인식을 이용하여 전화를 교환해주는 자동 교환 시스템을 구현하고, 성능을 평가하였다. 구현된 시스템에는 필수적인 음성인식 이외에도 DSP 진단 기능, 인식 대상 어휘의 추가 및 변경기능, 음성 수집 기능 등이 구현 되었다. SCHMM (Semi-Continuous Hidden Markov Model)을 이용한 전화망에서의 화자 독립 고립 단어 가변 어휘 인식을 대상으로 하였으며, 실시간 구현을 위하여 Texas Instrument 사의 TMS320C32를 사용하였다〔6〕. 인식 어휘는 부서명 및 인명이고 1300여 단어일 때, 인식 성능은 91.5%이다.

• The Journal of the Acoustical Society of Korea
• /
• v.19 no.4
• /
• pp.31-36
• /
• 2000

This paper describes the implementation and the evaluation of the speech recognition automatic exchange system. The system provides government or public offices, companies, educational institutions that are composed of large number of members and parts with exchange service using speech recognition technology. The recognizer of the system is a Speaker-Independent, Isolated-word, Flexible-Vocabulary recognizer based on SCHMM(Semi-Continuous Hidden Markov Model). For real-time implementation, DSP TMS320C32 made in Texas Instrument Inc. is used. The system operating terminal including the diagnosis of speech recognition DSP and the alternation of speech recognition candidates makes operation easy. In this experiment, 8 speakers pronounced words of 1,300 vocabulary related to automatic exchange system over wire telephone network and the recognition system achieved 91.5% of word accuracy.

• The Journal of the Acoustical Society of Korea
• /
• v.15 no.2
• /
• pp.5-11
• /
• 1996

The purpose of this paper is to propose a method improving the performance of a semi-continuous hidden Markov model(SCHMM) speaker adaptation system which uses Bayesian Parameter reestimation approach. The performance of Bayesian speaker adaptation could be degraded in case that the features of a new speaker are severely different from those of a reference codebook. The excessive codewords of the reference codebook still remain after adaptation proess. which cause confusion in recognition process. To solve such problems, the proposed method uses formant information which is extracted from the cepstral coefficients of the reference codebook and adaptation data. The reference codebook is adapted to represent the formant distribution of a new speaker and it is used for Bayesian speaker adaptation as an initial codebook. The proposed method provides accurate correspondence between reference codebook and adaptation data. It was observed that the excessive codewords were not selected during recognition process. The experimental results showed that the proposed method improved the recognition performance.

• The Journal of the Acoustical Society of Korea
• /
• v.18 no.7
• /
• pp.112-117
• /
• 1999

In case of spectral subtraction for noise robust speech recognition system, this method often makes loss of speech signal. In this study, we propose a method that variation and determination of Gaussian function at semi-continuous HMM(Hidden Markov Model) is made on the basis of SNR criteria function, in which SNR means signal to noise ratio between estimation noise and subtracted signal per frame. For proving effectiveness of this method, we show the estimation error to be related with the magnitude of estimated noise through signal waveform. For this reason, Gaussian function is varied and determined by SNR. When we test recognition rate by computer simulation under the noise environment of driving car over the speed of 80㎞/h, the proposed Gaussian decision method by SNR turns out to get more improved recognition rate compared with the frequency subtracted and non-subtracted cases.

• Journal of applied mathematics & informatics
• /
• v.31 no.5_6
• /
• pp.711-732
• /
• 2013

In this paper, we are interested in finding explicit numerical formulas to evaluate defaultable bonds prices of firms. For this purpose, we use a default intensity whose values depend on the credit rating of these firms. Each credit rating corresponds to a state of the default intensity. Then, this regime switches as soon as one of the credit rating of a firm also changes. Moreover, this regime switching default intensity model allows us to capture well some market features or economics behaviors. Thus, we obtain two explicit different formulas to evaluate the conditional Laplace transform of a regime switching Cox Ingersoll Ross model. One using the property of semi-affine of the model and the other one using analytic approximation. We conclude by giving some numerical illustrations of these formulas and real data estimation results.

• 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 Institute of Control, Robotics and Systems
• /
• v.6 no.6
• /
• pp.433-440
• /
• 2000

To flexibly evaluate performance and reliability of a real-time system which is intrinsically characterized by stringent timing constraints to generate correct responses, we propose fuzzyrandom variables and build a discrete event model embedded with fuzzy-random variables. Also, we adapt fuzzy-variables to a path-space approach, which derives the upper and lower bounds of reliability by using a semi-Markov model that explicitly contains the deadline information. Consequently, we propose certain formulas of state automata properly transformed by fuzzy-random variables, and present numerical examples applying the formulas to RTP(Rapid Thermal Process) to show that a complex system can be properly evaluated based on this model by computer simulation.

• The Transactions of the Korean Institute of Electrical Engineers D
• /
• v.49 no.7
• /
• pp.363-369
• /
• 2000

To flexibly evaluate performance and reliability of an electric power system in the aspect of the real-time system which is intrinsically characterized by stringent timing constraints fails catastrophically if its control input is not updated by its digital controller computer within a certain time limit called the hard deadline, we propose fuzzy-random variables and build a discrete event model embedded with fuzzy-random variables. Also, we adapt fuzzy-variables to a path-space approach, which derives the upper and lower bounds of reliability by using a semi-Markov model that explicitly contains the deadline information. Consequently, we propose certain formulas of state automata properly transformed by fuzzy-random variables, and present numerical examples applying the formulas as well.

• Journal of information and communication convergence engineering
• /
• v.18 no.4
• /
• pp.207-215
• /
• 2020

Part of speech (POS) tagging is an indispensable part of major NLP models. Its progress can be perceived on number of languages around the globe especially with respect to European languages. But considering Indian Languages, it has not got a major breakthrough due lack of supporting tools and resources. Particularly for Odia language it has not marked its dominancy yet. With a motive to make the language Odia fit into different NLP operations, this paper makes an attempt to develop a POS tagger for the said language on a HMM (Hidden Markov Model) platform. The tagger judiciously considers bigram HMM with dynamic Viterbi algorithm to give an output annotated text with maximum accuracy. The model is experimented on a corpus belonging to tourism domain accounting to a size of approximately 0.2 million tokens. With the proportion of training and testing as 3:1, the proposed model exhibits satisfactory result irrespective of limited training size.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.28 no.2B
• /
• pp.215-224
• /
• 2008

The effect of streamflow considering future land use change and vegetation index information by climate change scenario was assessed using SLURP (Semi-distributed Land-Use Runoff Process) model. The model was calibrated and verified using 4 years (1999-2002) daily observed streamflow data for the upstream watershed ($260.4km^2$) of Gyeongan water level gauging station. By applying CA-Markov technique, the future land uses (2030, 2060, 2090) were predicted after test the comparison of 2004 Landsat land use and 2004 CA-Markov land use by 1996 and 2000 land use data. The future land use showed a tendency that the forest and paddy decreased while urban, grassland and bareground increased. The future vegetation indices (2030, 2060, 2090) were estimated by the equation of linear regression between monthly NDVI of NOAA AVHRR images and monthly mean temperature of 5 years (1998-2002). Using CCCma CGCM2 simulation result based on SRES A2 and B2 scenario (2030s, 2060s, 2090s) of IPCC and data were downscaled by Stochastic Spatio-Temporal Random Cascade Model (SST-RCM) technique, the model showed that the future runoff ratio was predicted from 13% to 34% while the runoff ratio of 1999-2002 was 59%. On the other hand, the impact on runoff ratio by land use change showed about 0.1% to 1% increase.