|The dissertation consists of this summary and the following
papers, listed in chronological order of publication, except for Paper
4 - its position is moved back to indicate the time of creation because
of the delay to the publication. Section 4 of the summary is an extended
version of a presentation (Ström, 1995) at the IEEE Workshop on Automatic
Speech Recognition, 1995. This extended version is not previously published.
Paper 1. Nikko Ström (1994): "Optimising the Lexical Representation to Speed Up A* Lexical Search," STL QPSR 2-3/1994, pp. 113-124, (Paper, postscript 225KB).
Paper 2. Nikko Ström (1995): "A Speaker Sensitive Artificial Neural Network Architecture for Speaker Adaptation," ATR Technical Report, TR-IT-0116, ATR, Japan.
Paper 3. Nikko Ström (1996): "Continuous Speech Recognition in the WAXHOLM Dialogue System," STL QPSR 4/1996, pp. 67-96, (Paper, postscript 2391KB).
Paper 4. Nikko Ström (1997): "Speaker Modeling for Speaker Adaptation in Automatic Speech Recognition," in: Talker Variability in Speech Processing, Chapter 9, pp. 167-190, Eds: Keith Johnson & John Mullennix, Academic Press, ISBN 0-12-386560-3.
Paper 5. Nikko Ström (1996): "Speaker Adaptation by Modeling the Speaker Variation in a Continuous Speech Recognition System," Proc. ICSLP '96, Philadelphia, pp. 989-992, (Paper, postscript 314KB).
Paper 6. Nikko Ström (1997): "Phoneme Probability Estimation
with Dynamic Sparsely Connected Artificial Neural Networks,"The
Free Speech Journal (http://www.cse.ogi.edu/CSLU/fsj/),
Vol. 1, Issue #5. (paper,