Accessing Language Specific Linguistic Information for Triphone Model Generation: Feature Tables in a Speech Recognition System
- This paper is concerned with a novel methodology for generating phonetic questions used in tree-based state tying for speech recognition. In order to implement a speech recognition system, language-dependent knowledge which goes beyond annotated material is usually required. The approach presented here generates phonetic questions for decision trees are based on a feature table that summarizes the articulatory characteristics of each sound. On the one hand, this method allows better language-specific triphone models to be defined given only a feature-table as linguistic input. On the other hand, the feature-table approach facilitates efficient definition of triphone models for other languages since again only a feature table for this language is required. The approach is exemplified with speech recognition systems for English and Thai.
| Author: | Supphanat Kanokphara, Anja Geumann, Julie Carson-Berndsen |
|---|---|
| URN: | urn:nbn:de:bsz:mh39-57064 |
| URL: | http://citeseerx.ist.psu.edu/viewdoc/download?doi=10.1.1.58.7693&rep=rep1&type=pdf |
| ISBN: | 83-7177-341-2 |
| Parent Title (English): | Proceedings of the 2nd Language & Technology Conference: Human Language Technologies as a Challenge for Computer Science and Linguistics, April 21-23, Poznań, Poland (L&TC'05) |
| Publisher: | Wydawnictwo Poznańskie |
| Place of publication: | Poznań |
| Editor: | Zygmunt Vetulani |
| Document Type: | Conference Proceeding |
| Language: | English |
| Year of first Publication: | 2005 |
| Date of Publication (online): | 2016/12/13 |
| Publicationstate: | Postprint |
| GND Keyword: | Automatische Lauterkennung; Automatische Spracherkennung; Englisch; Thailändisch |
| First Page: | 7 |
| Last Page: | 10 |
| DDC classes: | 400 Sprache / 400 Sprache, Linguistik |
| Open Access?: | ja |
| BDSL-Classification: | Sprache im 20. Jahrhundert. Gegenwartssprache |
| Licence (German): | Creative Commons - Namensnennung-Nicht kommerziell-Keine Bearbeitung 3.0 Deutschland |


