Next: LIST OF ABBREVIATIONS
Up: No Title
Previous: Contents
The thesis consists of an introduction and the following publications:
- 1.
- 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.
- 2.
- 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.
- 3.
- 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,
Neural Networks for Signal Processing IV,
Proceedings of the IEEE Workshop on Neural
Networks for Signal Processing, NNSP'94,
pages 362-371, Ermioni, Greece, 1994.
- 4.
- Mikko Kurimo.
Segmental LVQ3 training for phoneme-wise tied mixture density HMMs.
In Giovanni Ramponi, Giovanni L. Sicuranza, Sergio Carrato,
Stefano Marsi, editors,
Signal Processing VIII,
Proceedings of the European Signal
Processing Conference, EUSIPCO'96,
pages 1599-1602, Trieste, Italy, 1996.
- 5.
- Mikko Kurimo and Panu Somervuo.
Using the Self-Organizing Map to speed up the probability density estimation
for speech recognition with mixture density HMMs.
In Proceedings of the International Conference on
Spoken Language Processing, ICSLP'96,
pages, 358-361, Philadelphia, PA, USA, 1996.
- 6.
- Mikko Kurimo.
Training mixture density HMMs with SOM and LVQ.
Helsinki University of Technology,
Laboratory of Computer and Information Science,
Report A43, January 1997, 26 pages.
Also submitted for publication in a journal.
Next: LIST OF ABBREVIATIONS
Up: No Title
Previous: Contents
Mikko Kurimo
11/7/1997