• Proceedings of the KSPS conference
• /
• 2005.04a
• /
• pp.87-90
• /
• 2005

Today's state-of the-art speech recognition systems typically use continuous distribution hidden Markov models with the mixtures of Gaussian distributions. To obtain higher recognition accuracy, the hidden Markov models typically require huge number of Gaussian distributions. Such speech recognition systems have problems that they require too much memory to run, and are too slow for large applications. Many approaches are proposed for the design of compact acoustic models. One of those models is subspace distribution clustering hidden Markov model. Subspace distribution clustering hidden Markov model can represent original full-space distributions as some combinations of a small number of subspace distribution codebooks. Therefore, how to make the codebook is an important issue in this approach. In this paper, we report some experimental results on various quantization methods to make more accurate models.

• The Journal of the Acoustical Society of Korea
• /
• v.8 no.1
• /
• pp.81-87
• /
• 1989

This paper discribes the method associated with modeling of Korean phonemes. Hidden Markov models(HMM's) may be viewed as an effective technique for modeling the inherent nonstationarity of speech signal. We propose a 3-state phoneme model to represent the sequentially changing characteristics of phonemes, i.e., transition-to-stationary-to-transition. Also we clarify that the duration of a phoneme is an important factor to have an effect in recognition accuracy and show that improvement in recognition rate can be obtained by using duration-dependent 3-state hidden Markov models.

• International journal of advanced smart convergence
• /
• v.7 no.1
• /
• pp.15-23
• /
• 2018

Spectrum allocation is a key operation in cognitive radio networks (CRNs), where secondary users (SUs) are usually selfish - to achieve itself utility maximization. In view of this context, much prior lit literature proposed spectrum allocation base on non-cooperative game models. However, the most of them proposed non-cooperative game models based on complete information of CRNs. In practical, primary users (PUs) in a dynamic wireless environment with noise uncertainty, shadowing, and fading is difficult to attain a complete information about them. In this paper, we propose a non-cooperative game joint hidden markov model scheme for spectrum allocation in CRNs. Firstly, we propose a new hidden markov model for SUs to predict the sensing results of competitors. Then, we introduce the proposed hidden markov model into the non-cooperative game. That is, it predicts the sensing results of competitors before the non-cooperative game. The simulation results show that the proposed scheme improves the energy efficiency of networks and utilization of SUs.

• Journal of Korea Multimedia Society
• /
• v.20 no.9
• /
• pp.1502-1508
• /
• 2017

A musical key is a fundamental concept in Western music theory. It is a collective characterization of pitches and chords that together create a musical perception of the entire piece. It is based on a group of pitches in a scale with which a music is constructed. Each key specifies the set of seven primary chromatic notes that are used out of the twelve possible notes. This paper presents a method that identifies the key of a song using Hidden Markov Models given a sequence of chroma features. Given an input song, a sequence of chroma features are computed. It is then classified into one of the 24 keys using a discrete Hidden Markov Models. The proposed method can help musicians and disc-jockeys in mixing a segment of tracks to create a medley. When tested on 120 songs, the success rate of the music key identification reached around 87.5%.

• Journal of the Korean Data and Information Science Society
• /
• v.18 no.4
• /
• pp.945-953
• /
• 2007

In this paper, we propose a smoothing and thus noise-reducing method of data sequences for stock price prediction with hidden Markov models, HMMs. The suggested method just uses simple moving average. A proper average size is obtained from forecasting experiments with stock prices of bank sector of Korean Exchange. Forecasting method with HMM and moving average smoothing is compared with a conventional method.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.17 no.11
• /
• pp.1199-1205
• /
• 1992

In this paper, a Korean word recognition method which usese Neural Network and Hidden Markov Models(HMM) is proposed to improve a recognition rate with a small amount of learning data. The method reduces the fluctuation due to personal differences which is a problem to a HMM recognition system. In this method, effective recognizer is designed by the complement of each recognition result of the Hidden Markov Models(HMM) and Neural Network. In order to evaluate this model, word recognition experiment is carried out for 28 cities which is DDD area names uttered by two male and a female in twenties. As a result of testing HMM with 8 state, codeword is 64, the recognition rate 91[%], as a result of testing Neural network(NN) with 64 codeword the recognition rate is 89[%]. Finally, as a result of testing NN-HMM with 64 codeword which the best condition in former tests, the recognition rate is 95[%].

• Transactions of the Korean Society for Noise and Vibration Engineering
• /
• v.21 no.2
• /
• pp.146-153
• /
• 2011

Model based machine condition diagnosis methods are generally using a normal and many failure models which need sufficient data to train the models. However, data, especially for failure modes of interest, is very hard to get in real applications. So their industrial applications are either severely limited or impossible when the failure models cannot be trained. In this paper, continuous hidden Markov model(CHMM) with only a normal model has been suggested as a very promising machine condition diagnosis method which can be easily used for industrial applications. Generally hidden Markov model also uses many pattern models to recognize specific patterns and the recognition results of CHMM show the likelihood trend of models. By observing this likelihood trend of a normal model, it is possible to detect failures. This method has been successively applied to arc weld defect diagnosis. The result shows CHMM's big potential as a machine condition monitoring method.

• The KIPS Transactions:PartB
• /
• v.14B no.7
• /
• pp.523-530
• /
• 2007

This paper proposes a new stochastic optimization algorithm for hidden Markov models (HMMs) used as a recognizer of automatic lipreading. The proposed method combines a global stochastic optimization method, the simulated annealing technique, and the local optimization method, which produces fast convergence and good solution quality. We mathematically show that the proposed algorithm converges to the global optimum. Experimental results show that training HMMs by the method yields better lipreading performance compared to the conventional training methods based on local optimization.

• 한국HCI학회:학술대회논문집
• /
• 2006.02a
• /
• pp.772-779
• /
• 2006

The new model proposed in this paper is the hidden Markov mesh model or the 2D HMM with the causality of top-down and left-right direction. With the addition of the causality constraint, two algorithms for the evaluation of a model and the maximum likelihood estimation of model parameters have been developed theoretically which are based on the forward-backward algorithm. It is a more natural extension of the 1D HMM than other 2D models. The proposed method will provide a useful way of modeling highly variable image patterns such as offline cursive characters.

• Journal of the Korean Institute of Telematics and Electronics
• /
• v.27 no.4
• /
• pp.636-644
• /
• 1990

Hidden Markov models(HMM's) have been known to be useful representation for speech signal and are used in a wide variety of speech systems. For speech recognition applications, it is desirable to incorporate durational information of states in model which correspond to phonetic duration of speech segments. In this paper we propose duration-dependent HMM's that include durational information of states appropriately for the left-to-right model. Reestimation formulae for the parameters of the proposed model are derived and their convergence is verified. Finally, the performance of the proposed models is verified by applying to an isolated word, speaker independent speech recognition system.