MAP Based Speaker Adaptation in Very Large Vocabulary Speech Recognition of Czech
The paper deals with the problem of efficient adaptation of speechrecognition systems to individual users. The goal is to achieve betterperformance in specific applications where one known speaker isexpected. In our approach we adopt the MAP (Maximum A Posteriori)method for this purpose. The MAP bas...
Main Authors: | J. Nouza, P. Cerva |
---|---|
Format: | Article |
Language: | English |
Published: |
Spolecnost pro radioelektronicke inzenyrstvi
2004-09-01
|
Series: | Radioengineering |
Online Access: | http://www.radioeng.cz/fulltexts/2004/04_03_42_46.pdf |
Similar Items
-
Speaker normalisation and adaptation in large vocabulary speech recognition
by: Uebel, Luís Felipe
Published: (2004) -
Bayesian Discriminative Speaker Adaptation for Large Vocabulary Continuous Speech Recognition
by: Chih-Hsien Huang, et al.
Published: (2006) -
Phonetic Alphabet for Speech Recognition of Czech
by: J. Uhlir, et al.
Published: (1997-12-01) -
Continuous mandarin speech recognition with very large vocabulary
by: Wang, Xin Min, et al.
Published: (1995) -
Cost-Efficient Development of Acoustic Models for Speech Recognition of Related Languages
by: J. Nouza, et al.
Published: (2013-09-01)