• Title/Summary/Keyword: HMM

Search Result 961, Processing Time 0.032 seconds

Analysis of Elm Topology Optimization Criteria for Handwriting Recognition (필기 데이터 인식을 위한 HMM 구조 최적화 기준에 대한 분석)

  • 박미나;하진영
    • Proceedings of the Korean Information Science Society Conference
    • /
    • 2002.10d
    • /
    • pp.571-573
    • /
    • 2002
  • 음성인식과 온라인 필기인식에서 우수한 성능을 보이는 은닉 마르코프(HMM)의 HMM의 구조는 휴리스틱 한 방법에 의해 결정되는 것이 일반적이기 때문에 최적의 모델을 선택하는데 어려움이 있다. 이에 본 논문에서는 HMM의 구조를 체계적인 방법으로 정함과 동시에 변별력의 단점을 개선 할 수 있는 방법으로 Anti-likelihood를 이용한 모델간의 변별력을 살펴보고 최적의 모델 선택 기준인 BIC와의 결합하여, 체계적이고 효율적인 최적 모델 선택이 가능한 방법론에 대해 연구하고 필기데이터에 대해 검증한 결과, 기존의 방법보다 파라미터의 수는 감소되고 인식률이 향상됨을 알 수 있다.

  • PDF

Causal 2D Hidden Markov Model (인과 2D 은닉 마르코프 모델)

  • Sin, Bong-Gi
    • Journal of KIISE:Software and Applications
    • /
    • v.28 no.1
    • /
    • pp.46-51
    • /
    • 2001
  • 2D로 확장한 HMM은 다수 제안되었지만 엄밀한 의미에 있어서 2D HMM이라고 하기에 부족한 점이 많다. 본 논문에서는 기존의 랜덤 필드 모형이 아닌 새로운 2D HMM을 제안한다. 상하 및 좌우 방향의 causal chain 관계를 가정하고 완전한 격자 형성 조건을 두어 2D HMM의 평가, 매개 변수를 추정하는 알고리즘을 제시하였다. 각각의 알고리즘은 동적 프로그래밍과 최우 추정법에 근거한 것이다. 변수 추정 알고리즘은 반복적으로 이루어지며 국소 최적치에 수렴함을 보였다.

  • PDF

Speaker Adaptation in HMM-based Korean Isoklated Word Recognition (한국어 격리단어 인식 시스템에서 HMM 파라미터의 화자 적응)

  • 오광철;이황수;은종관
    • The Transactions of the Korean Institute of Electrical Engineers
    • /
    • v.40 no.4
    • /
    • pp.351-359
    • /
    • 1991
  • This paper describes performances of speaker adaptation using a probabilistic spectral mapping matrix in hidden-Markov model(HMM) -based Korean isolated word recognition. Speaker adaptation based on probabilistic spectral mapping uses a well-trained prototype HMM's and is carried out by Viterbi, dynamic time warping, and forward-backward algorithms. Among these algorithms, the best performance is obtained by using the Viterbi approach together with codebook adaptation whose improvement for isolated word recognition accuracy is 42.6-68.8 %. Also, the selection of the initial values of the matrix and the normalization in computing the matrix affects the recognition accuracy.

Development of Daily Rainfall Simulation Model Based on Homogeneous Hidden Markov Chain (동질성 Hidden Markov Chain 모형을 이용한 일강수량 모의기법 개발)

  • Kwon, Hyun-Han;Kim, Tae Jeong;Hwang, Seok-Hwan;Kim, Tae-Woong
    • KSCE Journal of Civil and Environmental Engineering Research
    • /
    • v.33 no.5
    • /
    • pp.1861-1870
    • /
    • 2013
  • A climate change-driven increased hydrological variability has been widely acknowledged over the past decades. In this regards, rainfall simulation techniques are being applied in many countries to consider the increased variability. This study proposed a Homogeneous Hidden Markov Chain(HMM) designed to recognize rather complex patterns of rainfall with discrete hidden states and underlying distribution characteristics via mixture probability density function. The proposed approach was applied to Seoul and Jeonju station to verify model's performance. Statistical moments(e.g. mean, variance, skewness and kurtosis) derived by daily and seasonal rainfall were compared with observation. It was found that the proposed HMM showed better performance in terms of reproducing underlying distribution characteristics. Especially, the HMM was much better than the existing Markov Chain model in reproducing extremes. In this regard, the proposed HMM could be used to evaluate a long-term runoff and design flood as inputs.

A Study on the Voice Dialing using HMM and Post Processing of the Connected Digits (HMM과 연결 숫자음의 후처리를 이용한 음성 다이얼링에 관한 연구)

  • Yang, Jin-Woo;Kim, Soon-Hyob
    • The Journal of the Acoustical Society of Korea
    • /
    • v.14 no.5
    • /
    • pp.74-82
    • /
    • 1995
  • This paper is study on the voice dialing using HMM and post processing of the connected digits. HMM algorithm is widely used in the speech recognition with a good result. But, the maximum likelihood estimation of HMM(Hidden Markov Model) training in the speech recognition does not lead to values which maximize recognition rate. To solve the problem, we applied the post processing to segmental K-means procedure are in the recognition experiment. Korea connected digits are influenced by the prolongation more than English connected digits. To decrease the segmentation error in the level building algorithm some word models which can be produced by the prolongation are added. Some rules for the added models are applied to the recognition result and it is updated. The recognition system was implemented with DSP board having a TMS320C30 processor and IBM PC. The reference patterns were made by 3 male speakers in the noisy laboratory. The recognition experiment was performed for 21 sort of telephone number, 252 data. The recognition rate was $6\%$ in the speaker dependent, and $80.5\%$ in the speaker independent recognition test.

  • PDF

A study on the new hybrid recurrent TDNN-HMM architecture for speech recognition (음성인식을 위한 새로운 혼성 recurrent TDNN-HMM 구조에 관한 연구)

  • Jang, Chun-Seo
    • The KIPS Transactions:PartB
    • /
    • v.8B no.6
    • /
    • pp.699-704
    • /
    • 2001
  • ABSTRACT In this paper, a new hybrid modular recurrent TDNN (time-delay neural network)-HMM (hidden Markov model) architecture for speech recognition has been studied. In TDNN, the recognition rate could be increased if the signal window is extended. To obtain this effect in the neural network, a high-level memory generated through a feedback within the first hidden layer of the neural network unit has been used. To increase the ability to deal with the temporal structure of phonemic features, the input layer of the network has been divided into multiple states in time sequence and has feature detector for each states. To expand the network from small recognition task to the full speech recognition system, modular construction method has been also used. Furthermore, the neural network and HMM are integrated by feeding output vectors from the neural network to HMM, and a new parameter smoothing method which can be applied to this hybrid system has been suggested.

  • PDF

An Efficient Model Parameter Compensation Method foe Robust Speech Recognition

  • Chung Yong-Joo
    • MALSORI
    • /
    • no.45
    • /
    • pp.107-115
    • /
    • 2003
  • An efficient method that compensates the HMM parameters for the noisy speech recognition is proposed. Instead of assuming some analytical approximations as in the PMC, the proposed method directly re-estimates the HMM parameters by the segmental k-means algorithm. The proposed method has shown improved results compared with the conventional PMC method at reduced computational cost.

  • PDF

A Study on the Characteristics of Segmental-Feature HMM (분절특징 HMM의 특성에 관한 연구)

  • Yun Young-Sun;Jung Ho-Young
    • MALSORI
    • /
    • no.43
    • /
    • pp.163-178
    • /
    • 2002
  • In this paper, we discuss the characteristics of Segmental-Feature HMM and summarize previous studies of SFHMM. There are several approaches to reduce the number of parameters in the previous studies. However, if the number of parameters decreased, the performance of systems also fell. Therefore, we consider the fast computation approach with preserving the same number of parameters. In this paper, we present the new segment comparison method to speed up the computation of SFHMM without loss of performance. The proposed method uses the three-frame calculation rather than the full(five) frames in the given segment. The experimental results show that the performance of the proposed system is better than that of the previous studies.

  • PDF

HMM-Based Transient Identification in Dynamic Process

  • Kwon, Kee-Choon
    • Transactions on Control, Automation and Systems Engineering
    • /
    • v.2 no.1
    • /
    • pp.40-46
    • /
    • 2000
  • In this paper, a transient identification based on a Hidden Markov Model (HMM) has been suggested and evaluated experimentally for the classification of transients in the dynamic process. The transient can be identified by its unique time dependent patterns related to the principal variables. The HMM, a double stochastic process, can be applied to transient identification which is a spatial and temporal classification problem under a statistical pattern recognition framework. The HMM is created for each transient from a set of training data by the maximum-likelihood estimation method. The transient identification is determined by calculating which model has the highest probability for the given test data. Several experimental tests have been performed with normalization methods, clustering algorithms, and a number of states in HMM. Several experimental tests have been performed including superimposing random noise, adding systematic error, and untrained transients. The proposed real-time transient identification system has many advantages, however, there are still a lot of problems that should be solved to apply to a real dynamic process. Further efforts are being made to improve the system performance and robustness to demonstrate reliability and accuracy to the required level.

  • PDF

Recognition of isolated digits using Predictive RBF Network (Predictive RBFN을 이용한 단독 숫자음 인식)

  • Han Hag-Yong;Kim Sang-Berm;Kim Joo-Sung;Kim Soo-Hoon;Hur Kang-In
    • Proceedings of the Acoustical Society of Korea Conference
    • /
    • autumn
    • /
    • pp.71-76
    • /
    • 1999
  • 본 논문에서 제안한 예측형 RBFN(Radial Basis Function Network)은 HMM과 신경망을 결합한 하이브리드 구조이다. 이 신경망은 HMM으로 추정한 확률분포 파라미터를 사용하여 중간층의 활성화 함수의 출력을 결정하고, 중간층과 출력층의 연결강도만 네트워크 내에서 학습한다. 그리고 HMM으로 추정한 확률분포 파라미터는 두 가지 방법으로 예측형 RBFN에 이용하였다. 첫 번째는 HMM의 각 상태의 혼합수 만큼의 중간층 유니트를 주는 방법이고, 두 번째는 HMM의 혼합수$\times$출력분포수 만큼의 중간층 유니트를 주는 방법이다. 실험결과, 예측형 RBFN은 다른 방법들의 결과보다 $4.5\~6.5\%$ 저하된 결과를 보였지만 다른 신경망에 비해서 학습 반복 횟수를 작게할 수 있었으며 전체 학습시간을 대폭 단축할 수 있었다.

  • PDF