References

Amari, 1967

Amari, S. (1967).
A theory of adaptive pattern classifiers.
IEEE Transactions on Electronic Computers, 16(3):299-307.

Bahl et al., 1986

Bahl, L., Brown, P., de Souza, P., and Mercer, R. (1986).
Maximum mutual information estimation of hidden Markov model parameters for speech recognition.
In Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pages 49-52.

Bahl et al., 1988

Bahl, L., Brown, P., de Souza, P., and Mercer, R. (1988).
A new algorithm for the estimation of hidden Markov model parameters.
In Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pages 493-496.

Baker, 1975

Baker, J. M. (1975).
The DRAGON system - an overview.
IEEE Transactions on Acoustics, Speech, and Signal Processing, 23(1):24-29.

Baldi and Chauvin, 1996

Baldi, P. and Chauvin, Y. (1996).
Hybrid modeling, HMM/NN architectures, and protein applications.
Neural Computation, 8:1541-1561.

Bauer et al., 1996

Bauer, H.-U., Der, R., and Herrmann, M. (1996).
Controlling the magnification factor of self-organizing feature maps.
Neural Computation, 8(4):757-771.

Baum, 1972

Baum, L. (1972).
An inequality and associated maximization technique in statistical estimation of probabilistic functions of Markov processes.
Inequalities, 3:1-8.

Baum and Petrie, 1966

Baum, L. and Petrie, T. (1966).
Statistical inference for probabilistic functions of finite state Markov chains.
Annals of Mathematical Statistics, 37:1554-1563.

Bellegarda and Nahamoo, 1990

Bellegarda, J. and Nahamoo, D. (1990).
Tied mixture continuous parameter modeling for speech recognition.
IEEE Transactions on Acoustics, Speech, and Signal Processing, 38(12):2033-2045.

Bocchieri, 1993

Bocchieri, E. (1993).
Vector quantization for the efficient computation of continuous density likelihoods.
In Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), volume 2, pages 692-695.

Bourlard, 1995

Bourlard, H. (1995).
Towards increasing speech recognition error rates.
In Proceedings of 4th European Conference on Speech Communication and Technology, pages 883-894, Madrid, Spain.

Bourlard and Wellekens, 1990

Bourlard, H. and Wellekens, C. J. (1990).
Links between Markov models and multilayer perceptrons.
IEEE Transactions on Pattern Analysis and Machine Intelligence, 12(12):1167-1178.

Bradburn, 1989

Bradburn, D. (1989).
Reducing transmission error effects using a self-organizing network.
In Proceedings of the International Joint Conference on Neural Networks (IJCNN), volume 2, pages 531-537, Piscataway, NJ. IEEE Service Center.

Chang and Juang, 1992

Chang, P.-C. and Juang, B.-H. (1992).
Discriminative template training for dynamic programming speech recognition.
In Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), volume 1, pages 493-496, San Francisco,USA.

Cho and Kim, 1995

Cho, S.-B. and Kim, J. H. (1995).
An HMM/MLP architecture for sequence recognition.
Neural Computation, 7:358-369.

Chou et al., 1992

Chou, W., Juang, B., and Lee, C. (1992).
Segmental GPD training of HMM based speech recognizer.
In Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), volume 1, pages 473-476, San Francisco,USA.

Cottrell and Fort, 1987

Cottrell, M. and Fort, J.-C. (1987).
Étude d'un processus d'auto-organisation.
Annales de l'Institut Henri Poincaré, 23(1):1-20.
(in French).

Cottrell et al., 1997

Cottrell, M., Fort, J.-C., and Pages, G. (1997).
Theoretical aspects of the SOM algorithm.
In Workshop on Self-Organizing Maps, pages 246-267, Espoo, Finland.

Digalakis et al., 1996

Digalakis, V., Monaco, P., and Murveit, H. (1996).
Genones: Generalized mixture tying in continuous hidden Markov model-based speech recognizers.
IEEE Transactions on Speech and Audio Processing, 4(4):281-289.

Dugast et al., 1994

Dugast, C., Devillers, L., and Aubert, X. (1994).
Combining TDNN and HMM in a hybrid system for improved continuous-speech recognition.
IEEE Transactions on Speech and Audio Processing, 2(1):217-223.

Erwin et al., 1992a

Erwin, E., Obermayer, K., and Schulten, K. (1992a).
Self-organizing maps: Ordering, convergence properties and energy functions.
Biological Cybernetics, 67(1):47-55.

Erwin et al., 1992b

Erwin, E., Obermayer, K., and Schulten, K. (1992b).
Self-organizing maps: Stationary states, metastability and convergence rate.
Biological Cybernetics, 67(1):35-45.

Feller, 1966

Feller, W. (1966).
An Introduction to Probability Theory and its Applications, volume II.
John Wiley & Sons Inc., New York.

Flanagan, 1996

Flanagan, J. A. (1996).
Self-organisation in Kohonen's SOM.
Neural Networks, 9(7):1185-1197.

Forney, 1973

Forney, G. D. (1973).
The Viterbi algorithm.
Proceedings of the IEEE, 61(3):268-278.

Fort and Pages, 1996

Fort, J.-C. and Pages, G. (1996).
About the Kohonen algorithm: Strong or weak self-organization?
Neural Networks, 9(5):773-785.

Franzini et al., 1990

Franzini, M., Lee, K.-F., and Waibel, A. (1990).
Connectionist Viterbi training: a new hybrid method for continuous speech recognition.
In Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), volume 1, pages 425-428, Albuquerque, NM.

Friedman et al., 1975

Friedman, J., Baskett, F., and Shustek, L. (1975).
An algorithm for finding nearest neighbors.
IEEE Transactions on Computers, 24:1000-1006.

Galindo, 1995

Galindo, P. L. (1995).
A competitive algorithm for training HMM for speech recognition.
In Proceedings of 4th European Conference on Speech Communication and Technology, pages 2187-2190, Madrid, Spain.

Gauvain and Lee, 1994

Gauvain, J.-L. and Lee, C.-H. (1994).
Maximum a posteriori estimation for multivariate Gaussian mixture observations of Markov chains.
IEEE Transactions on Speech and Audio Processing, 2(2):291-298.

Gillick and Cox, 1989

Gillick, L. and Cox, S. (1989).
Some statistical issues in the comparison of speech recognition algorithms.
In Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pages 532-535, Glasgow, Scotland.

Gorin and Mammone, 1994

Gorin, A. and Mammone, R. J. (1994).
Introduction to the special issue on neural networks for speech processing.
IEEE Transactions on Speech and Audio Processing, 2(1):113-114.

Hämäläinen, 1995

Hämäläinen, A. (1995).
Self-organizing Map and Reduced Kernel Density Estimation.
PhD thesis, University of Jyväskylä, Jyväskylä, Finland.

Holmström and Hämäläinen, 1993

Holmström, L. and Hämäläinen, A. (1993).
The self-organizing reduced kernel density estimator.
In Proceedings of the International Conference on Neural Networks (ICNN), pages 417-421, Piscataway, NJ. IEEE Service Center.

Huang and Lippmann, 1991

Huang, W. Y. and Lippmann, R. P. (1991).
HMM speech recognition with neural net discrimination.
In Lippmann, R. P., Moody, J. E., and Touretzky, D. S., editors, Advances in Neural Information Processing Systems 3, pages 194-202. Morgan Kaufmann, San Mateo, CA.

Huang and Jack, 1989

Huang, X. and Jack, M. (1989).
Semi-continuous hidden Markov models for speech signals.
Computer Speech and Language, 3(3):239-252.

Huo et al., 1995

Huo, Q., Chan, C., and Lee, C.-H. (1995).
Bayesian adaptive learning of the parameters of hidden Markov model for speech recognition.
IEEE Transactions on Speech and Audio Processing, 3(5):334-345.

Iwamida et al., 1990

Iwamida, H., Katagiri, S., McDermott, E., and Tohkura, Y. (1990).
A hybrid speech recognition system using HMMs with an LVQ-trained codebook.
In Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), volume 1, pages 489-492.

Jalanko, 1980

Jalanko, M. (1980).
Studies of Learning Projective Methods in Automatic Speech Recognition.
PhD thesis, Helsinki University of Technology, Espoo, Finland.

Jelinek, 1976

Jelinek, F. (1976).
Continuous speech recognition by statistical methods.
Proceedings of the IEEE, 64(4):532-536.

Jelinek and Mercer, 1980

Jelinek, F. and Mercer, R. (1980).
Interpolated estimation of Markov source parameters from sparse data.
In Proceedings of an International Workshop on Pattern Recognition in Practice, Amsterdam, The Netherlands. North-Holland.

Juang, 1985

Juang, B.-H. (1985).
Maximum likelihood estimation for mixture multivariate stochastic observation of Markov chains.
AT&T Technical Journal, 64(6):1235-1249.

Juang and Katagiri, 1992

Juang, B.-H. and Katagiri, S. (1992).
Discriminative learning for minimum error classification.
IEEE Transactions on Signal Processing, 40(12):3043-3054.

Juang and Rabiner, 1990

Juang, B.-H. and Rabiner, L. R. (1990).
The segmental K-means algorithm for estimating parameters of hidden Markov models.
IEEE Transactions on Acoustics, Speech, and Signal Processing, 38(9):1639-1641.

Juang and Rabiner, 1991

Juang, B.-H. and Rabiner, L. R. (1991).
Hidden Markov models for speech recognition.
Technometrics, 33(3):251-272.

Kangas, 1995

Kangas, J. (1995).
Increasing the error tolerance in transmission of vector quantized images by self-organizing maps.
In Fogelman-Soulié, F. and Gallinari, P., editors, Proceedings of ICANN'95, International Conference on Artificial Neural Networks, volume 1, pages 287-291. EC2 et Cie.

Kapadia et al., 1993

Kapadia, S., Valtchev, V., and Young, S. (1993).
MMI training for continuous phoneme recognition on the TIMIT database.
In Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), volume 2, pages 491-494.

Kaski, 1997

Kaski, S. (1997).
Data Exploration Using Self-Organizing Maps.
PhD thesis, Helsinki University of Technology, Espoo, Finland.

Kasslin et al., 1992

Kasslin, M., Kangas, J., and Simula, O. (1992).
Process state monitoring using self-organizing maps.
In Aleksander, I. and Taylor, J., editors, Artificial Neural Networks, 2, volume I, pages 1532-1534, Amsterdam, Netherlands. North-Holland.

Katagiri and Lee, 1993

Katagiri, S. and Lee, C.-H. (1993).
A new hybrid algorithm for speech recognition based on HMM segmentation and learning vector quantization.
IEEE Transactions on Speech and Audio Processing, 1(4):421-430.

Katagiri et al., 1991

Katagiri, S., Lee, C.-H., and Juang, B.-H. (1991).
New discriminative training algorithms based on the generalized probabilistic descent method.
In Proceedings of the IEEE Workshop on Neural Networks for Signal Processing, pages 298-308, Princeton, New Jersey, USA.

Kim et al., 1994

Kim, D.-S., Lee, S.-Y., Han, M.-S., Lee, C.-H., Park, J.-G., and Suh, S.-W. (1994).
Multi-dimensional HMM parameter estimation using self-organizing feature map for speech recognition.
In Proceedings of the 3rd International Conference on Fuzzy Logic, Neural Nets and Soft Computing, pages 541-542, Iizuka, Japan. Fuzzy Logic Systems Institute.

Kohonen, 1982

Kohonen, T. (1982).
Clustering, taxonomy, and topological maps of patterns.
In Proc. 6ICPR, Int. Conf. on Pattern Recognition, pages 114-128, Washington, DC. IEEE Computer Soc. Press.

Kohonen, 1986a

Kohonen, T. (1986a).
Dynamically expanding context, with application to the correction of symbol strings in recognition of continuous speech.
In Proceedings of the 8th International Conference on Pattern Recognition, pages 1148-1151, Paris, France.

Kohonen, 1986b

Kohonen, T. (1986b).
Learning vector quantization for pattern recognition.
Report TKK-F-A601, Helsinki University of Technology, Espoo, Finland.

Kohonen, 1990a

Kohonen, T. (1990a).
Improved versions of learning vector quantization.
In Proceedings of the International Joint Conference on Neural Networks (IJCNN), volume 1, pages 545-550, San Diego, California.

Kohonen, 1990b

Kohonen, T. (1990b).
The self-organizing map.
Proceedings of the IEEE, 78(9):1464-1480.

Kohonen, 1991

Kohonen, T. (1991).
Workstation-based phonetic typewriter.
In Proceedings of the IEEE Workshop on Neural Networks for Signal Processing, pages 279-288, Princeton, New Jersey, USA.

Kohonen, 1992

Kohonen, T. (1992).
New developments of learning vector quantization and the self-organizing map.
In Symposium on Neural Networks; Alliances and Perspectives in Senri (SYNAPSE'92), Osaka, Japan. Senri Int. Information Institute.

Kohonen, 1993

Kohonen, T. (1993).
Things you haven't heard about the self-organizing map.
In Proceedings of the International Conference on Neural Networks (ICNN), pages 1147-1156, Piscataway, NJ. IEEE Service Center.

Kohonen, 1995

Kohonen, T. (1995).
Self-Organizing Maps.
Springer, Berlin.

Kohonen, 1996

Kohonen, T. (1996).
The speedy SOM.
Technical Report A33, Helsinki University of Technology, Laboratory of Computer and Information Science, Espoo, Finland.

Kohonen et al., 1988

Kohonen, T., Barna, G., and Chrisley, R. (1988).
Statistical pattern recognition with neural networks: Benchmarking studies.
In Proceedings of the International Conference on Neural Networks (ICNN), volume I, pages 61-68, Los Alamitos, CA. IEEE Computer Soc. Press.

Kohonen et al., 1996a

Kohonen, T., Hynninen, J., Kangas, J., and Laaksonen, J. (1996a).
SOM_PAK: the self-organizing map programming package.
Report A31, Helsinki University of Technology, Laboratory of Computer and Information Science, Espoo, Finland.
Program package available via WWW at URL http://nucleus.hut.fi/nnrc/som_pak.

Kohonen et al., 1996b

Kohonen, T., Hynninen, J., Kangas, J., Laaksonen, J., and Torkkola, K. (1996b).
LVQ_PAK: the learning vector quantization programming package.
Report A30, Helsinki University of Technology, Laboratory of Computer and Information Science, Espoo, Finland.
Program package available via WWW at URL http://nucleus.hut.fi/nnrc/lvq_pak.

Kohonen et al., 1996c

Kohonen, T., Kaski, S., Lagus, K., and Honkela, T. (1996c).
Very large two-level SOM for the browsing of newsgroups.
In von der Malsburg, C., von Seelen, W., Vorbrüggen, J. C., and Sendhoff, B., editors, Proceedings of ICANN96, International Conference on Artificial Neural Networks, Bochum, Germany, July 16-19, 1996, Lecture Notes in Computer Science, vol. 1112, pages 269-274. Springer, Berlin.

Kohonen et al., 1996d

Kohonen, T., Oja, E., Simula, O., Visa, A., and Kangas, J. (1996d).
Engineering application of the self-organizing map.
Proceedings of the IEEE, 84(10):1358-1384.

Koikkalainen, 1995

Koikkalainen, P. (1995).
Fast deterministic self-organizing maps.
In Fogelman-Soulié, F. and Gallinari, P., editors, Proceedings of ICANN'95, International Conference on Artificial Neural Networks Paris, France, 9-13 October 1995, volume 2, pages 63-68. EC2 et Cie.

Koikkalainen and Oja, 1990

Koikkalainen, P. and Oja, E. (1990).
Self-organizing hierarchical feature maps.
In Proceedings of the International Joint Conference on Neural Networks (IJCNN), volume II, pages 279-284, Piscataway, NJ. IEEE Service Center.

Komori and Katagiri, 1992

Komori, T. and Katagiri, S. (1992).
GPD training of dynamic programming-based speech recognizers.
J. Acoustical Society of Japan, 13(6):341-349.

Komori et al., 1995

Komori, Y., Yamada, M., Yamamoto, H., and Ohora, Y. (1995).
An efficient output probability computation for continuous HMM using rough and detailed models.
In Proceedings of 4th European Conference on Speech Communication and Technology, pages 1087-1090, Madrid, Spain.

Kurimo, 1992

Kurimo, M. (1992).
Combinations of adaptive vector quantization methods and hidden Markov models in speech recognition.
Master's thesis, Helsinki University of Technology, Espoo, Finland.
(in Finnish).

Kurimo, 1994

Kurimo, M. (1994).
Application of learning vector quantization and self-organizing maps for training continuous density and semi-continuous Markov models.
Licentiate's Thesis, Helsinki University of Technology, Espoo, Finland.

Kurimo, 1997

Kurimo, M. (1997).
SOM based density function approximation for mixture density HMMs.
In Workshop on Self-Organizing Maps, pages 8-13, Espoo, Finland.

Kurimo and Torkkola, 1992a

Kurimo, M. and Torkkola, K. (1992a).
Application of SOMs and LVQ in training continuous density hidden Markov models.
In Proceedings of the International Conference on Spoken Language Processing, volume 1, pages 543-546, Banff, Canada.

Kurimo and Torkkola, 1992b

Kurimo, M. and Torkkola, K. (1992b).
Combining LVQ with continuous density hidden Markov models in speech recognition.
In Proceedings of the SPIE's Conference on Neural and Stochastic Methods in Image and Signal Processing, volume 1766, pages 726-734, San Diego, USA.

Lampinen and Oja, 1989

Lampinen, J. and Oja, E. (1989).
Fast self-organization by the probing algorithm.
In Proceedings of the International Joint Conference on Neural Networks (IJCNN), volume II, pages 503-507, Piscataway, NJ. IEEE Service Center.

Lee et al., 1990

Lee, C.-H., Lin, C.-H., and Juang, B.-H. (1990).
A study on speaker adaptation of continuous density HMM parameters.
In Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), volume 1, pages 145-148.

Liporace, 1982

Liporace, L. A. (1982).
Maximum likelihood estimation for multivariate observations of Markov sources.
IEEE Transactions on Information Theory, 28(5):729-734.

Lippmann, 1989

Lippmann, R. (1989).
Review of neural networks for speech recognition.
Neural Computation, 1(1):1-38.

Ljolje et al., 1990

Ljolje, A., Ephraim, Y., and Rabiner, L. (1990).
Estimation of hidden Markov model parameters by minimizing empirical error rate.
In Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pages 709-712.

Lopez-Gonzalo and Hernandez-Gomez, 1993

Lopez-Gonzalo, E. and Hernandez-Gomez, L. A. (1993).
Fast vector quantization using neural maps for CELP at 2400 bps.
In Proceedings of 3rd European Conference on Speech Communication and Technology, volume 1, pages 55-58, Berlin, Germany.

Luttrell, 1990

Luttrell, S. P. (1990).
Derivation of a class of training algorithms.
IEEE Trans. on Neural Networks, 1(2):229-232.

MacQueen, 1967

MacQueen, J. (1967).
Some methods for classification and analysis of multivariate observations.
In Proceedings of Fifth Berkeley Symposium on Math. Statist. and Prob., pages 281-297.

Makhoul et al., 1985

Makhoul, J., Roucos, S., and Gish, H. (1985).
Vector quantization in speech coding.
Proceedings of IEEE, 73(11):1551-1588.

Makino et al., 1992

Makino, S., Endo, M., Sone, T., and Kido, K. (1992).
Recognition of phonemes in continuous speech using a modified LVQ2 method.
J. Acoustical Society of Japan, 13(6):351-360.

Mäntysalo, 1992

Mäntysalo, J. (1992).
Some experiments on LVQ-based speech recognition with high-dimensional context vectors.
Master's thesis, Helsinki University of Technology.
(in Finnish).

McDermott, 1990

McDermott, E. (1990).
LVQ3 for phoneme recognition.
In Proc. Spring Meet. Acoust. Soc. Jpn., pages 151-152.

McDermott and Katagiri, 1994

McDermott, E. and Katagiri, S. (1994).
Prototype-based minimum classification error/ generalized probabilistic descent training for various speech units.
Computer Speech and Language, 8(4):351-368.

Mizuta and Nakajima, 1990

Mizuta, S. and Nakajima, K. (1990).
An optimal discriminative training method for continuous mixture density HMMs.
In Proceedings of the International Conference on Spoken Language Processing, volume 1, pages 245-248, Kobe,Japan.

Monte, 1992

Monte, E. (1992).
Smoothing HMMs by means of a SOM.
In Proceedings of 1992 International Conference on Spoken Language Processing, volume 1, pages 535-537, Banff, Canada.

Morgan and Bourlard, 1995

Morgan, N. and Bourlard, H. (1995).
Neural networks for statistical recognition of continuous speech.
Proceedings of the IEEE, 83(5):742-770.

Mulier and Cherkassky, 1995

Mulier, F. and Cherkassky, V. (1995).
Self-organization as an iterative kernel smoothing process.
Neural Computation, 7(6):1165-1177.

Niles and Silverman, 1990

Niles, L. T. and Silverman, H. F. (1990).
Combining hidden Markov model and neural network classifiers.
In Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), volume 1, pages 417-420.

Nilsson, 1965

Nilsson, N. (1965).
Learning Machines.
McGraw-Hill, New York.

Parzen, 1962

Parzen, E. (1962).
On estimation of a probability density function and mode.
Annals of Mathematical Statistics, 33:1065-1076.

Paul, 1989

Paul, D. B. (1989).
The Lincoln robust continuous speech recognizer.
In Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), volume 1, pages 449-452, Glasgow, Scotland.

Peinado et al., 1994

Peinado, A. M., Segura, J. C., Rubio, A. J., and Benitez, M. C. (1994).
Using multiple vector quantization and semicontinuous hidden Markov models for speech recognition.
In Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), volume 1, pages 61-64.

Rabiner et al., 1983

Rabiner, L., Levinson, S., and Sondhi, M. (1983).
On the application of vector quantization and hidden Markov models to speaker-independent isolated word recognition.
Bell System Technical Journal, 62:1075-1105.

Rabiner et al., 1986

Rabiner, L., Wilpon, J., and Juang, B. (1986).
A segmental K-means training procedure for connected word recognition.
AT&T Technical Journal, 64:21-40.

Rabiner, 1989

Rabiner, L. R. (1989).
A tutorial on hidden Markov models and selected applications in speech recognition.
Proceedings of the IEEE, 77(2):257-286.

Rabiner, 1994

Rabiner, L. R. (1994).
Applications of voice processing to telecommunications.
Proceedings of the IEEE, 82(2):199-228.

Rainton and Sagayama, 1992

Rainton, D. and Sagayama, S. (1992).
Appropriate error criterion selection for continuous speech HMM minimum error training.
In Proceedings of the International Conference on Spoken Language Processing, volume 1, pages 233-236, Banff,Canada.

Renals et al., 1991

Renals, S., Morgan, N., and Bourlard, H. (1991).
Probability estimation by feed-forward networks in continuous speech recognition.
In Proceedings of the IEEE Workshop on Neural Networks for Signal Processing, pages 309-318, Princeton, New Jersey, USA.

Renals et al., 1994

Renals, S., Morgan, N., Bourlard, H., Cohen, M., and Franco, H. (1994).
Connectionist probability estimators in HMM speech recognition.
IEEE Transactions on Speech and Audio Processing, 2(1):161-174.

Renals et al., 1992

Renals, S., Morgan, N., Bourlard, H., Franco, H., and Cohen, M. (1992).
Connectionist optimization of tied mixture hidden Markov models.
In Lippmann, R. P., Moody, J. E., and Touretzky, D. S., editors, Advances in Neural Information Processing Systems 3, pages 167-174. Morgan Kaufmann, San Mateo, CA.

Ritter, 1989

Ritter, H. (1989).
Asymptotic level density for a class of vector quantization processes.
Report A9, Helsinki University of Technology, Laboratory of Computer and Information Science, Espoo, Finland.

Ritter, 1991

Ritter, H. (1991).
Asymptotic level density for a class of vector quantization processes.
IEEE Transactions on Neural Networks, 2(1):173-175.

Ritter and Schulten, 1986

Ritter, H. and Schulten, K. (1986).
On the stationary state of Kohonen's self-organizing sensory mapping.
Biological Cybernetics, 54(1):99-106.

Ritter and Schulten, 1988

Ritter, H. and Schulten, K. (1988).
Convergence properties of Kohonen's topology preserving maps: fluctuations, stability, and dimension selection.
Biological Cybernetics, 60(1):59-71.

Robbins and Monro, 1951

Robbins, H. and Monro, S. (1951).
A stochastic approximation method.
Annals of Mathematical Statistics, 22:400-407.

Segura et al., 1994

Segura, J., Rubio, A., Peinado, A., Garcia, P., and Roman, R. (1994).
Multiple VQ hidden Markov modelling for speech recognition.
Speech Communication, 14:163-170.

Seide, 1995

Seide, F. (1995).
Fast likelihood computation for continuous mixture densities using a tree-based nearest neighbor search.
In Proceedings of 4th European Conference on Speech Communication and Technology, pages 1079-1082, Madrid, Spain.

Singer and Lippmann, 1992

Singer, E. and Lippmann, R. P. (1992).
A speech recognizer using radial basis function neural networks in an HMM framework.
In Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), volume 1, pages 629-632, San Francisco,USA.

Torkkola et al., 1991

Torkkola, K., Kangas, J., Utela, P., Kaski, S., Kokkonen, M., Kurimo, M., and Kohonen, T. (1991).
Status report of the Finnish phonetic typewriter project.
In Kohonen, T., Mäkisara, K., Simula, O., and Kangas, J., editors, Artificial Neural Networks, volume I, pages 771-776, Amsterdam, Netherlands. North-Holland.

Utela, 1992

Utela, P. (1992).
Phoneme recognition with discrete density Markov models.
Master's thesis, Helsinki University of Technology.
(in Finnish).

Young, 1996

Young, S. (1996).
A review of large-vocabulary continuous-speech recognition.
IEEE Signal Processing Magazine, pages 45-57.

Young and Woodland, 1994

Young, S. and Woodland, P. (1994).
State clustering in HMM based speech recognition.
Computer Speech and Language, 8(4):369-384.

Zador, 1982

Zador, P. L. (1982).
Asymptotic quantization error of continuous signals and the quantization dimension.
IEEE Transactions on Information Theory, IT-28(2):139-148.

Zhao and Rowden, 1991

Zhao, Z. and Rowden, C. (1991).
Application of Kohonen self-organising feature maps to smoothing parameters of hidden Markov models for speech recognition.
In Second Int. Conf. on Artificial Neural Networks (Conf. Publ. No.349), pages 175-179, London, UK. IEE.