Name
Abstract | ||
|---|---|---|
The statistical pattern recognition is a promising framework for text-to-text translation. However, a natural extension to speech-input translation is not straightforward. In this paper, we present a method to deal with the speech input statistical translation problem that could be considered as a step towards a fully integrated recognition-translation procedure. In this version, a word graph was used in the input as a representation of the acoustic of a given utterance. As a case study, experimental results with the so-called "Traveler task" are presented by using a text-input statistical translator. |
Year | DOI | Venue |
|---|---|---|
2000 | 10.1109/ICPR.2000.903492 | ICPR |
Keywords | Field | DocType |
recognition-translation procedure,speech-input statistical translation,traveler task,speech input statistical translation,promising framework,text-to-text translation,text-input statistical translator,statistical pattern recognition,new approach,natural extension,case study,speech recognition,natural languages,language translation,transducers,dynamic programming,graph theory,pattern recognition,speech processing,decoding,iterative methods,probability | Cache language model,Language translation,Computer science,Utterance,Feature (machine learning),Artificial intelligence,Natural language processing,Language model,Graph theory,Dynamic programming,Pattern recognition,Word error rate,Speech recognition | Conference |
ISSN | Citations | PageRank |
1051-4651 | 5 | 0.54 |
References | Authors | |
6 | 3 | |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Ismael García-varea | 1 | 275 | 36.16 |
| Alberto Sanchis | 2 | 73 | 7.67 |
| francisco casacuberta | 3 | 1439 | 161.33 |