1 / 16

A Hybrid Model of HMM and RBFN Model of Speech Recognition

A Hybrid Model of HMM and RBFN Model of Speech Recognition. 길이만 , 김수연 , 김성호 , 원윤정 , 윤아림 한국과학기술원 응용수학전공. Automatic Speech Recognition. • Message Encoding /Decoding. Hidden Markov Models. The Markov Generation Model. Hidden Markov Models. •. HMM is defined by :

dyan
Télécharger la présentation

A Hybrid Model of HMM and RBFN Model of Speech Recognition

An Image/Link below is provided (as is) to download presentation Download Policy: Content on the Website is provided to you AS IS for your information and personal use and may not be sold / licensed / shared on other websites without getting consent from its author. Content is provided to you AS IS for your information and personal use only. Download presentation by click this link. While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server. During download, if you can't get a presentation, the file might be deleted by the publisher.

E N D

Presentation Transcript


  1. A Hybrid Model of HMM and RBFN Model of Speech Recognition 길이만, 김수연,김성호, 원윤정,윤아림 한국과학기술원 응용수학전공

  2. Automatic Speech Recognition • Message Encoding /Decoding

  3. Hidden Markov Models • The Markov Generation Model

  4. Hidden Markov Models • HMM is defined by : 1. A set S of Q states, , of a time-discrete Markov chain of order 1 2. An initial probability distribution of the states : 3. A transition probability distribution between states: 4. An emission probability distribution of the acoustic observations X within each state:

  5. Hidden Markov Models • Major problems of HMMs – Trainig – Decoding • Solutions:– Baum/Welch algorithm– Viterbi algorithm

  6. Hidden Markov Models • Advantages of standard HMMs – provide a natural and highly reliable way of recognizing speech for a wide range of applications – integrate well into systems incorporating both task syntax and semantics • Limitations of standard HMMs – non-discriminative training/decoding criterion – Arbitrary assumptions on the parametric form of probability distributions – High sensitivity to environmental conditions

  7. Artificial Neural Networks • Nice Properties of ANN * Learning Capability from examples* Generalization ability* Non-parametric estimation • Limitations of ANN * Restricted to local decisions – generally used for classification of static input with no sequential processing* Not well-suited for dealing with time-varying Input patterns and segmentation of sequential inputs

  8. Hybrid Models of HMM/ANN • ANNs that emulate HMMs • Connectionist probability estimation for continuous HMMs • Hybrids with "global optimization" • Connectionist Vector Quantizers for discrete HMMs • ANNs as acoustic front-ends for continuous HMMs

  9. Hybrid Models of HMM/ANN 1. Initialization: – Initial segmentation of the training set – Labeling of the acoustic vectors with "0" or "1" ,according to the segmentation – ANN training via Back-Propagation (BP) or other algorithms 2. Iteration – New segmentation of training set according to Viterbi algorithm computed over ANN outputs – Labeling of the acoustic vectors with "0" or "1" – ANN retaining by BP

  10. Proposed HMM/RBFN Model

  11. Proposed HMM/RBFN Model • First Training • LBG clustering – Setting centers and variances of radial basis functions • RLS algorithm – Training weights – Target:

  12. 2. Second Training-LCM/GPD

  13. Simulation • Database – TIMIT1Five class phoneme (C, L, N, S, V)Acoustic features: 26 dimension of MFCC features – TIMIT2Digit(0, 1, 2, …,9) Acoustic features: 16 dimension of ZCPA features

  14. Simulation 2. Results – TIMIT1 Table 1: result of 5 class recognition

  15. – TIMIT2 Table2: result of Digit recognition

  16. Conclusion 1. Result – Non-parametric estimates: no a priori assumpitions on the form of the distributions – Better initialization than other hybrid system – Discriminative training – Improved performance over standard HMM 2. Further Works – Performance degration in noise environment – Clustering/Parameter Training – GPD is not stable

More Related