| Title: | A direct criterion minimization based fMLLR via gradient descend |
| Authors: | Vaněk, Jan Zajíc, Zbyněk |
| Citation: | VANĚK, Jan; ZAJÍC, Zbyněk. A direct criterion minimization based fMLLR via gradient descend. In: Text, speech and dialogue. Berlin: Springer, 2013, p. 52-59. (Lectures notes in computer science; 8082). ISBN 978-3-642-40584-6. |
| Issue Date: | 2013 |
| Publisher: | Springer |
| Document type: | článek article |
| URI: | http://www.kky.zcu.cz/cs/publications/JanVanek_2013_ADirectCriterion http://hdl.handle.net/11025/17162 |
| ISBN: | 978-3-642-40584-6 |
| Keywords: | ASR;fMLLR;adaptace |
| Keywords in different language: | ASR;fMLLR;adaptation |
| Abstract in different language: | Adaptation techniques are necessary in automatic speech recognizers to improve a recognition accuracy. Linear Transformation methods (MLLR or fMLLR) are the most favorite in the case of limited available data. The fMLLR is the feature-space transformation. This is the advantage with contrast to MLLR that transforms the entire acoustic model. The classical fMLLR estimation involves maximization of the likelihood criterion based on individual Gaussian components statistic.We proposed an approach which takes into account the overall likelihood of a HMMstate. It estimates the transformation to optimize the ML criterion of HMM directly using gradient descent algorithm. |
| Rights: | © Jan Vaněk - Zbyněk Zajíc |
| Appears in Collections: | Články / Articles (NTIS) |
Files in This Item:
| File | Description | Size | Format | |
|---|---|---|---|---|
| JanVanek_2013_ADirectCriterion.pdf | Plný text | 101,06 kB | Adobe PDF | View/Open |
Please use this identifier to cite or link to this item:
http://hdl.handle.net/11025/17162Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.