Bottleneck ANN: dealing with small amount of data in shift-MLLR adaptation
| dc.contributor.author | Zajíc, Zbyněk | |
| dc.contributor.author | Machlica, Lukáš | |
| dc.contributor.author | Müller, Luděk | |
| dc.date.accessioned | 2015-12-10T09:44:20Z | |
| dc.date.available | 2015-12-10T09:44:20Z | |
| dc.date.issued | 2012 | |
| dc.description.abstract | Článek popisuje řešení nedostatečného množství dat pro shift-MLLR adaptaci pomocí neuonové sítě bottelneck. | cs |
| dc.description.abstract-translated | The aim of this work is to propose a refinement of the shift-MLLR (shift Maximum Likelihood Linear Regression) adaptation of an acoustics model in the case of limited amount of adaptation data, which can lead to ill-conditioned transformations matrices. We try to suppress the influence of badly estimated transformation parameters utilizing the bottleneck Artificial Neural Network (ANN). The ill-conditioned shift-MLLR transformation is propagated through a bottleneck ANN (suitably trained beforehand), and the output of the net is used as the new refined transformation. To train the ANN the well and the badly conditioned shift-MLLR transformations are used as outputs and inputs of ANN, respectively. | en |
| dc.format | 4 s. | cs |
| dc.format.mimetype | application/pdf | |
| dc.identifier.citation | ZAJÍC, Zbyněk; MACHLICA, Lukáš; MüLLER, Luděk. Bottleneck ANN: dealing with small amount of data in shift-MLLR adaptation. In: IEEE 11th international conference on signal processing. Beijing: IEEE Press, 2012, p. 507-510. | en |
| dc.identifier.uri | http://www.kky.zcu.cz/cs/publications/ZbynekZajic_2012_BottleneckANN | |
| dc.identifier.uri | http://hdl.handle.net/11025/16950 | |
| dc.language.iso | en | en |
| dc.publisher | IEEE Press | en |
| dc.rights | © Zbyněk Zajíc - Lukáš Machlica - Luděk Müller | cs |
| dc.rights.access | openAccess | en |
| dc.subject | ASR | cs |
| dc.subject | adaptace | cs |
| dc.subject | shift-MLLR | cs |
| dc.subject | ANN | cs |
| dc.subject | bottleneck | cs |
| dc.subject.translated | ASR | en |
| dc.subject.translated | adaptation | en |
| dc.subject.translated | shift-MLLR | en |
| dc.subject.translated | ANN | en |
| dc.subject.translated | bottleneck | en |
| dc.title | Bottleneck ANN: dealing with small amount of data in shift-MLLR adaptation | en |
| dc.title.alternative | Bottleneck ANN: shift-MLLR adaptace pro malé množství dat | cs |
| 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:
- ZbynekZajic_2012_BottleneckANN.pdf
- Size:
- 168.33 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: