Title | ||
---|---|---|
The efficient generation of pronunciation dictionaries: machine learning factors during bootstrapping |
Abstract | ||
---|---|---|
Several factors affect the efficiency of bootstrapping approaches to the generation of pronunciation dictionaries. We focus on factors related to the underlying rule-extraction algorithms, and demonstrate variants of the Dynamically Expanding Context al- gorithm which are beneficial for this application. In particular, we show that continuous updating of the learned rules, cou- pled with a new approach to phoneme alignment and a sliding- window approach to choosing the context window, leads to an efficient and accurate bootstrapping mechanism. |
Year | Venue | Keywords |
---|---|---|
2004 | INTERSPEECH | machine learning,sliding window |
Field | DocType | Citations |
Bootstrapping (linguistics),Pronunciation,Spoken language processing,Pattern recognition,Computer science,Bootstrapping,Speech recognition,Natural language processing,Artificial intelligence | Conference | 5 |
PageRank | References | Authors |
0.89 | 6 | 2 |
Name | Order | Citations | PageRank |
---|---|---|---|
Marelie H. Davel | 1 | 236 | 22.70 |
Etienne Barnard | 2 | 24 | 3.19 |