Title | ||
---|---|---|
Continuous local codebook features for multi- and cross-lingual acoustic phonetic modelling |
Abstract | ||
---|---|---|
In this paper we present a method for defining the question set for the induction of acoustic phonetic decision trees. The method is data driven resulting in a continuous feature space in contrast to the usual categorical one. We apply the features to a multi- lingual speech recognition task, outperforming consistently the standard method using IPA-based characteristics. An extension to cross-lingual applications together with first preliminary results are given too. |
Year | Venue | Keywords |
---|---|---|
2005 | INTERSPEECH | feature space,decision tree,speech recognition |
Field | DocType | Citations |
Cross lingual,Pattern recognition,Computer science,Speech recognition,Artificial intelligence,Codebook | Conference | 0 |
PageRank | References | Authors |
0.34 | 6 | 3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Frank Diehl | 1 | 0 | 0.34 |
Asunción Moreno | 2 | 399 | 44.97 |
Enric Monte | 3 | 58 | 22.82 |