A direct criterion minimization based fMLLR via gradient descend
| dc.contributor.author | Vaněk, Jan | |
| dc.contributor.author | Zajíc, Zbyněk | |
| dc.date.accessioned | 2016-01-07T12:18:48Z | |
| dc.date.available | 2016-01-07T12:18:48Z | |
| dc.date.issued | 2013 | |
| dc.description.abstract-translated | 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. | en |
| dc.format | 8 s. | cs |
| dc.format.mimetype | application/pdf | |
| dc.identifier.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. | en |
| dc.identifier.doi | 10.1007/978-3-642-40585-3_8 | |
| dc.identifier.isbn | 978-3-642-40584-6 | |
| dc.identifier.uri | http://www.kky.zcu.cz/cs/publications/JanVanek_2013_ADirectCriterion | |
| dc.identifier.uri | http://hdl.handle.net/11025/17162 | |
| dc.language.iso | en | en |
| dc.publisher | Springer | en |
| dc.relation.ispartofseries | Lecture notes in computer science; 8082 | en |
| dc.rights | © Jan Vaněk - Zbyněk Zajíc | cs |
| dc.rights.access | openAccess | en |
| dc.subject | ASR | cs |
| dc.subject | fMLLR | cs |
| dc.subject | adaptace | cs |
| dc.subject.translated | ASR | en |
| dc.subject.translated | fMLLR | en |
| dc.subject.translated | adaptation | en |
| dc.title | A direct criterion minimization based fMLLR via gradient descend | en |
| dc.type | článek | cs |
| dc.type | article | en |
| dc.type.status | Peer-reviewed | en |
| dc.type.version | publishedVersion | en |
Files
Original bundle
1 - 1 out of 1 results
No Thumbnail Available
- Name:
- JanVanek_2013_ADirectCriterion.pdf
- Size:
- 101.06 KB
- Format:
- Adobe Portable Document Format
- Description:
- Plný text
License bundle
1 - 1 out of 1 results
No Thumbnail Available
- Name:
- license.txt
- Size:
- 1.71 KB
- Format:
- Item-specific license agreed upon to submission
- Description: