Mikko Kurimo

References

[Kohonen82] T. Kohonen. Self-organizing formation of topologically correct feature maps. Biological Cybernetics, 43(1):59--69, 1982.

[Kohonen90] T. Kohonen. The self-organizing map. Proceedings of IEEE, 78:1464--1480, 1990.

[Kohonen86] T. Kohonen. Learning Vector Quantization for Pattern Recognition Technical Report TKK-F-A601, Helsinki University of Technology, 1986.

[Kohonen90] T. Kohonen. The self-organizing map. Proceedings of IEEE, 78:1464--1480, 1990.

[Kohonen92] Teuvo Kohonen and Jari Kangas and Jorma Laaksonen and Kari Torkkola LVQ_PAK: A program package for the correct application of Learning Vector Quantization algorithms. Proceedings of the International Joint Conference on Neural networks (IJCNN), Baltimore, June, 1992.

[Rabiner89] Lawrence R. Rabiner A Tutorial on Hidden Markov Models and Selected Applications in Speech Recognition. Proceedings of the IEEE, volume 77, number 2, pages 257-286, 1989.

[Kohonen84] Teuvo Kohonen, Kai Mäkisara and Tapio Saramäki. Phonotopic maps - insightful representation of phonological features for speech recognition. In Proceedings of the 7th International Conference on Pattern Recognition (7th ICPR), pages 182-185, Montreal, Canada, July 1984.

[Kohonen87] Teuvo Kohonen, Kari Torkkola, Makoto Shozakai, Jari Kangas and Olli Ventä. Implementation of a large vocabulary speech recognizer and phonetic Typewriter for Finnish and Japanese. In Proceedings of the European Conference on Speech Technology, pages 377-380, Edinburgh, U.K., September 1987

[Kohonen88a] Teuvo Kohonen. The 'neural' phonetic typewriter. Computer. 21(3) 11-22. 1988.

[Kohonen88b] Teuvo Kohonen, Kari Torkkola, Makoto Shozakai, Jari Kangas and Olli Ventä. Phonetic Typewriter for Finnish and Japanese. Proceedings of the IEEE 1988 International Conference on Acoustics, Speech, and Signal Processing, pages 607-610, Piscataway, NJ, 1988. IEEE.

[Torkkola91] Kari Torkkola and Jari Kangas and Pekka Utela and Sami Kaski and Mikko Kokkonen and Mikko Kurimo and Teuvo Kohonen. Status report of the finnish phonetic typewriter project. Artificial Neural Networks, Editors: T. Kohonen and K. Mäkisara and O. Simula and J. Kangas, pages I-771-776, Espoo, Finland, 1991. North-Holland.

[Kurimo92a] Mikko Kurimo. Combinations of Learning Vector Quantization and Self-Organizing Maps with hidden Markov models in speech recognition. Master's Thesis, Helsinki Univ. of Tech., Lab. of Comp. and Inf. Science, FIN-02150 Espoo, Finland, 1992.

[Kurimo94a] Mikko Kurimo. Application of Learning Vector Quantization and Self-Organizing Maps for training continuous density and semicontinuous Markov models. Licentiate's Thesis, Helsinki Univ. of Tech., Lab. of Comp. and Inf. Science, FIN-02150 Espoo, Finland, 1994.

[Kurimo97] Mikko Kurimo. Using Self-Organizing Maps and Learning Vector Quantization for Mixture Density Hidden Markov Models. Doctorate Thesis, Helsinki Univ. of Tech., Lab. of Comp. and Inf. Science, FIN-02150 Espoo, Finland, 1997.

<[Torkkola91a] Kari Torkkola, Jari Kangas, Pekka Utela, Sami Kaski, Mikko Kokkonen, Mikko Kurimo, and Teuvo Kohonen. Status report of the Finnish phonetic typewriter project. In Proceedings of the International Conference on Artificial Neural Networks (ICANN-91), pages 771-776, Espoo, Finland, June 24-28 1991. North-Holland. Abstract Entire paper

<[Torkkola91b] Kari Torkkola and Mikko Kokkonen and Mikko Kurimo and Pekka Utela. Improving Short-Time Speech Frame Recognition Results by Using Context. In Proceedings of the 2nd European Conference on Speech Technology and Communication, EUROSPEECH'91, pages 793-796, Milano, Italy, 1991. Abstract Entire paper

[Kurimo92a] Mikko Kurimo. Combinations of adaptive vector quantization methods and hidden Markov models in speech recognition. Master's thesis, Helsinki University of Technology, February 1992. (in Finnish). Abstract Entire thesis (281 kB)

[Kurimo92b] Mikko Kurimo and Kari Torkkola Training Continuous Density Hidden Markov Models in Association with Self-Organizing Maps and LVQ. In Proceedings of the IEEE Workshop on Neural Networks for Signal Processing, pages 174-183, Copenhagen, Denmark, 1992. Abstract Entire paper (48 kB)

[Kurimo92c] Mikko Kurimo and Kari Torkkola 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, pages 726-734, San Diego, USA, 1992. Abstract Entire paper (48 kB)

[Kurimo92d] Mikko Kurimo and Kari Torkkola Application of SOMs and LVQ in training continuous density hidden Markov models. In Proceedings of the International Conference on Spoken Language Processing, ICSLP'92, pages 543-546, Banff, Canada, 1992. Abstract Entire paper (45 kB)

[Kurimo93] Mikko Kurimo. Using LVQ to enhance semi-continuous hidden Markov models for phonemes. In Proceedings of 3rd European Conference on Speech Communication and Technology, EUROSPEECH'93, pages 1731-1734, Berlin, Germany, 1993. Abstract Entire paper (52 kB)

[Kurimo94a] Mikko Kurimo. 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, February 1994. Abstract Entire thesis (316 kB)

[Kurimo94b] Mikko Kurimo. Corrective tuning by applying LVQ for continuous density and semi-continuous Markov models. In Proceedings of International Symposium on Speech, Image Processing and Neural Networks, ISSIPNN'94, pages 718-721, Hong Kong, 1994. Abstract Entire paper (31 kB)

[Kurimo94c] Mikko Kurimo. Hybrid training method for tied mixture density hidden Markov models using Learning Vector Quantization and Viterbi estimation. In John Vlontzos, Jenq-Neng Hwang, Elizabeth Wilson, editors, Proceedings of the IEEE Workshop on Neural Networks for Signal Processing, NNSP'94, pages 362-371, Ermioni, Greece, 1994. Abstract Entire paper (46 kB)