Robust statistic estimates for adaptation in the task of speech recognition
| dc.contributor.author | Zajíc, Zbyněk | |
| dc.contributor.author | Machlica, Lukáš | |
| dc.contributor.author | Müller, Luděk | |
| dc.date.accessioned | 2015-12-10T12:11:08Z | |
| dc.date.available | 2015-12-10T12:11:08Z | |
| dc.date.issued | 2010 | |
| dc.description.abstract | Tento článek se zabývá robustním odvozením statistik pro úlohu adaptace akustického modelu. Statistiky jsou akumulovány před vlastním procesem adaptace z dostupných adaptačních dat. Obecně se předpokládá malé množství těchto dat, která jsou často znehodnocena šumem, různým kanálem atd., proto jsme navrhli techniku, která má za úkol robustní odhat adaptace z takovýchto dat. Jednou z často užívaných metod je inicializace adaptačních tranformací. Druhá, námi navržená metoda spočívá v akumulování pouze vhodně rozpoznaných dat (statistik). Zameřili jsme se na metodu fMLLR, na které jsme provedli experimenty. | cs |
| dc.description.abstract-translated | This paper deals with robust estimations of data statistics used for the adaptation. The statistics are accumulated before the adaptation process from available adaptation data. In general, only small amount of adaptation data is assumed. These data are often corrupted by noise, channel, they do not contain only clean speech. Also, when training Hidden Markov Models (HMM) several assumptions are made that could not have been fulfilled in the praxis, etc. Therefore, we described several techniques that aim to make the adaptation as robust as possible in order to increase the accuracy of the adapted system. One of the methods consists in initialization of the adaptation statistics in order to prevent ill-conditioned transformation matrices. Another problem arises when an acoustic feature is assigned to an improper HMM state even if the reference transcription is available. Such situations can occur because of the forced alignment process used to align frames to states. Thus, it is quite handy to accumulate data statistic utilizing only reliable frames (in the sense of data likelihood). We are focusing on Maximum Likelihood Linear Transformations and the experiments were performed utilizing the feature Maximum Likelihood Linear Regression (fMLLR). Experiments are aimed to describe the behavior of the system extended by proposed methods. | en |
| dc.format | 8 s. | cs |
| dc.format.mimetype | application/pdf | |
| dc.identifier.citation | ZAJÍC, Zbyněk; MACHLICA, Lukáš; MÜLLER, Ludě›k. Robust statistic estimates for adaptation in the task of speech recognition. In: Lecture notes in computer science. Berlin: Springer, 6231/2010, p. 464-471. ISSN 0302-9743 | en |
| dc.identifier.issn | 0302-9743 | |
| dc.identifier.uri | http://www.kky.zcu.cz/cs/publications/ZbynekZajic_2010_RobustStatistic | |
| dc.identifier.uri | http://hdl.handle.net/11025/16953 | |
| dc.language.iso | en | en |
| dc.publisher | Springer | cs |
| dc.rights | © Zbyněk Zajíc - LukášMachlica - Luděk Müller | cs |
| dc.rights.access | openAccess | en |
| dc.subject | fMLLR | cs |
| dc.subject | adaptace | cs |
| dc.subject | rozpoznávání řeči | cs |
| dc.subject | robustnost | cs |
| dc.subject.translated | fMLLR | en |
| dc.subject.translated | adaptation | en |
| dc.subject.translated | speech recognition | en |
| dc.subject.translated | robustness | en |
| dc.title | Robust statistic estimates for adaptation in the task of speech recognition | en |
| dc.title.alternative | Robustní odhad statistik pro adaptaci v úloze rozpoznávání řeči | 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_2010_RobustStatistic.pdf
- Size:
- 166.99 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: