Segmental Hidden Markov Models with Random Effects for Waveform Modeling

This paper proposes a general probabilistic framework for shape-based modeling and classification of waveform data. A segmental hidden Markov model (HMM) is used to characterize waveform shape and shape variation is captured by adding random effects to the segmental model. The resulting probabilistic framework provides a basis for learning of waveform models from data as well as parsing and recognition of new waveforms. Expectation-maximization (EM) algorithms are derived and investigated for fitting such models to data. In particular, the "expectation conditional maximization either" (ECME) algorithm is shown to provide significantly faster convergence than a standard EM procedure. Experimental results on two real-world data sets demonstrate that the proposed approach leads to improved accuracy in classification and segmentation when compared to alternatives such as Euclidean distance matching, dynamic time warping, and segmental HMMs without random effects.

[1]  Mary P. Harper,et al.  On the complexity of explicit duration HMM's , 1995, IEEE Trans. Speech Audio Process..

[2]  D. Rubin,et al.  Estimation in Covariance Components Models , 1981 .

[3]  Michael C. Horsch,et al.  Dynamic Bayesian networks , 1990 .

[4]  A. Koski.  Modelling ECG signals with hidden Markov models , 1996, Artif. Intell. Medicine.

[5]  T. J. Bennett,et al.  Analysis of seismic discrimination capabilities using regional data from western United States events , 1986 .

[6]  Stephen J. Roberts,et al.  Markov Models for Automated ECG Interval Analysis , 2003, NIPS.

[7]  Nathan Intrator,et al.  Classification of seismic signals by integrating ensembles of neural networks , 1998, IEEE Trans. Signal Process..

[8]  D. Rubin,et al.  Maximum likelihood from incomplete data via the EM - algorithm plus discussions on the paper , 1977 .

[9]  Xiao-Li Meng,et al.  Maximum likelihood estimation via the ECM algorithm: A general framework , 1993 .

[10]  Christos Faloutsos,et al.  Fast Time Sequence Indexing for Arbitrary Lp Norms , 2000, VLDB.

[11]  N. Laird,et al.  Maximum likelihood computations with repeated measures: application of the EM algorithm , 1987 .

[12]  Yung-Hwan Oh,et al.  A segmental-feature HMM for speech pattern modeling , 2000, IEEE Signal Process. Lett..

[13]  Padhraic Smyth,et al.  Modeling Waveform Shapes with Random Eects Segmental Hidden Markov Models , 2004, UAI 2004.

[14]  Stephen E. Levinson,et al.  Continuously variable duration hidden Markov models for automatic speech recognition , 1986 .

[15]  D. Rubin,et al.  The ECME algorithm: A simple extension of EM and ECM with faster monotone convergence , 1994 .

[16]  J. Ware,et al.  Random-effects models for longitudinal data. , 1982, Biometrics.

[17]  Michael I. Jordan.  Learning in Graphical Models , 1999, NATO ASI Series.

[18]  Biing-Hwang Juang,et al.  Fundamentals of speech recognition , 1993, Prentice Hall signal processing series.

[19]  Brendan J. Frey,et al.  A segment based probabilistic generative model of speech , 2005, Proceedings. (ICASSP '05). IEEE International Conference on Acoustics, Speech, and Signal Processing, 2005..

[20]  Ada Wai-Chee Fu,et al.  Efficient time series matching by wavelets , 1999, Proceedings 15th International Conference on Data Engineering (Cat. No.99CB36337).

[21]  S. Jankowski,et al.  Computer-aided morphological analysis of Holter ECG recordings based on support vector learning system , 2003, Computers in Cardiology, 2003.

[22]  Padhraic Smyth,et al.  Deformable Markov model templates for time-series pattern matching , 2000, KDD '00.

[23]  Christos Faloutsos,et al.  Efficient Similarity Search In Sequence Databases , 1993, FODO.

[24]  SmythPadhraic,et al.  Segmental Hidden Markov Models with Random Effects for Waveform Modeling , 2006 .

[25]  Martin Russell,et al.  A segmental HMM for speech pattern modelling , 1993, 1993 IEEE International Conference on Acoustics, Speech, and Signal Processing.

[26]  H. H. Bruun,et al.  Hot-Wire Anemometry: Principles and Signal Analysis , 1996 .

[27]  Eamonn J. Keogh,et al.  Scaling up dynamic time warping for datamining applications , 2000, KDD '00.

[28]  Stuart J. Russell,et al.  Dynamic bayesian networks: representation, inference and learning , 2002 .

[29]  R. Moore,et al.  Explicit modelling of state occupancy in hidden Markov models for automatic speech recognition , 1985, ICASSP '85. IEEE International Conference on Acoustics, Speech, and Signal Processing.

[30]  Martin J. Russell,et al.  Probabilistic-trajectory segmental HMMs , 1999, Comput. Speech Lang..

[31]  Mari Ostendorf,et al.  From HMM's to segment models: a unified view of stochastic modeling for speech recognition , 1996, IEEE Trans. Speech Audio Process..

[32]  Mark J. F. Gales,et al.  The theory of segmental hidden Markov models , 1993 .

[33]  Eamonn J. Keogh,et al.  A Probabilistic Approach to Fast Pattern Matching in Time Series Databases , 1997, KDD.

[34]  Xiaodong Sun,et al.  Speech recognition using hidden Markov models with polynomial regression functions as nonstationary states , 1994, IEEE Trans. Speech Audio Process..