• Journal of Digital Convergence
• /
• v.12 no.7
• /
• pp.273-278
• /
• 2014

In vocabulary recognition using HMM(Hidden Markov Model) by model for the observation of a discrete probability distribution indicates the advantages of low computational complexity, but relatively low recognition rate. Improve them with a HMM model is proposed for the optimization of the Bayesian methods. In this paper is posterior distribution and prior distribution in recognition Gaussian mixtures model provides a model to optimize of the Bayesian methods vocabulary recognition. The result of applying the proposed method, the recognition rate of 97.9% in vocabulary recognition, respectively.

• MALSORI
• /
• no.59
• /
• pp.53-68
• /
• 2006

We report the evaluation results of the Korean speech recognition platform called ECHOS. The platform has an object-oriented and reusable architecture so that researchers can easily evaluate their own algorithms. The platform has all intrinsic modules to build a large vocabulary speech recognizer: Noise reduction, end-point detection, feature extraction, hidden Markov model (HMM)-based acoustic modeling, cross-word modeling, n-gram language modeling, n-best search, word graph generation, and Korean-specific language processing. The platform supports both lexical search trees and finite-state networks. It performs word-dependent n-best search with bigram in the forward search stage, and rescores the lattice with trigram in the backward stage. In an 8000-word continuous speech recognition task, the platform with a lexical tree increases 40% of word errors but decreases 50% of recognition time compared to the HTK platform with flat lexicon. ECHOS reduces 40% of recognition errors through incorporation of cross-word modeling. With the number of Gaussian mixtures increasing to 16, it yields word accuracy comparable to the previous lexical tree-based platform, Julius.

• Phonetics and Speech Sciences
• /
• v.1 no.1
• /
• pp.63-67
• /
• 2009

In this paper, in order to protect music copyrights, we propose a music identification system which is scalable to the number of pieces of registered music and robust to signal-level variations of registered music. For its implementation, we define the new concepts of 'music word' and 'music phoneme' as recognition units to construct 'music acoustic models'. Then, with these concepts, we apply the HMM-based framework used in continuous speech recognition to identify the music. Each music file is transformed to a sequence of 39-dimensional vectors. This sequence of vectors is represented as ordered states with Gaussian mixtures. These ordered states are trained using Baum-Welch re-estimation method. Music files with a suspicious copyright are also transformed to a sequence of vectors. Then, the most probable music file is identified using Viterbi algorithm through the music identification network. We implemented a music identification system for 1,000 MP3 music files and tested this system with variations in terms of MP3 bit rate and music speed rate. Our proposed music identification system demonstrates robust performance to signal variations. In addition, scalability of this system is independent of the number of registered music files, since our system is based on HMM method.

• Bulletin of the Korean Chemical Society
• /
• v.30 no.1
• /
• pp.177-182
• /
• 2009

We present the geminate rebinding kinetics measurements of CO to 2-methylimidazole (2-MeIm) bound ferrous protoporphyrin- IX (FePPIX) in alkaline glycerol/water mixtures at 293 K after photolysis. The kinetics was probed by monitoring the CO stretching mode using femtosecond vibrational spectroscopy. When 2-MeIm is used in excess, heme dimers that typically form in low viscosity solutions disappear as the viscosity of the solvent increases. Heme aggregates formed in low viscosity solutions turn monomeric as more 2-MeIm is added, suggesting that 6-coordinated heme, including a strong proximal histidine tends to be in the monomeric form. The vibrational band of CO in the 2-MeIM-FePPIX-CO is well described by a single Gaussian function centered at 1958 $cm^-1$ and 28 $cm^-1$ full width at half maximum. The efficiency and rate of the geminate rebinding of CO to the heme increase with viscosity of the solvent, suggesting that retention of the dissociated CO near the heme, for a longer period by the viscous solvent media, accelerates rebinding.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.17 no.8
• /
• pp.2259-2277
• /
• 2023

We propose a probabilistic fish growth model for smart aquaculture systems equipped with IoT sensors that monitor the ecological environment. As IoT sensors permeate into smart aquaculture systems, environmental data such as oxygen level and temperature are collected frequently and automatically. However, there still exists data on fish weight, tank allocation, and other factors that are collected less frequently and manually by human workers due to technological limitations. Unlike sensor data, human-collected data are hard to obtain and are prone to poor quality due to missing data and reading errors. In a situation where different types of data are mixed, it becomes challenging to develop an effective fish growth model. This study explores the unique characteristics of such a combined environmental and weight dataset. To address these characteristics, we develop a preprocessing method and a probabilistic fish growth model using mixed data sampling (MIDAS) and overlapping mixtures of Gaussian processes (OMGP). We modify the OMGP to be applicable to prediction by setting a proper prior distribution that utilizes the characteristic that the ratio of fish groups does not significantly change as they grow. We conduct a numerical study using the eel dataset collected from a real smart aquaculture system, which reveals the promising performance of our model.

• Steel and Composite Structures
• /
• v.43 no.5
• /
• pp.581-601
• /
• 2022

The main objective of this research work is to investigate the free vibration behavior of annular sandwich plates resting on the Kerr foundation at thermal conditions. This sandwich configuration is composed of two FGM face sheets as coating layer and a porous GPLRC (GPL reinforced composite) core. It is supposed that the GPL nanofillers and the porosity coefficient vary continuously along the core thickness direction. To model closed-cell FG porous material reinforced with GPLs, Halpin-Tsai micromechanical modeling in conjunction with Gaussian-Random field scheme is used, while the Poisson's ratio and density are computed by the rule of mixtures. Besides, the material properties of two FGM face sheets change continuously through the thickness according to the power-law distribution. To capture fundamental frequencies of the annular sandwich plate resting on the Kerr foundation in a thermal environment, the analysis procedure is with the aid of Reddy's shear-deformation plate theory based high-order shear deformation plate theory (HSDT) to derive and solve the equations of motion and boundary conditions. The governing equations together with related boundary conditions are discretized using the generalized differential quadrature (GDQ) method in the spatial domain. Numerical results are compared with those published in the literature to examine the accuracy and validity of the present approach. A parametric solution for temperature variation across the thickness of the sandwich plate is employed taking into account the thermal conductivity, the inhomogeneity parameter, and the sandwich schemes. The numerical results indicate the influence of volume fraction index, GPLs volume fraction, porosity coefficient, three independent coefficients of Kerr elastic foundation, and temperature difference on the free vibration behavior of annular sandwich plate. This study provides essential information to engineers seeking innovative ways to promote composite structures in a practical way.