Name
Abstract | ||
|---|---|---|
In this paper, we present a novel approach for morphological decomposition in large vocabulary Arabic speech recognition. It achieved low out-of-vocabulary (OOV) rate as well as high recognition accuracy in a state-of-the-art Arabic broadcast news transcription system. In this approach, the compound words are decomposed into stems and affixes in both language training and acoustic training data. The decomposed words in the recognition output are re-joined before scoring. Four algorithms are experimented and compared in this work. The best system achieved 1.9% absolute reduction (9.8% relative) in word error rate (WER) when compared to the 64K-word baseline. The recognition performance of this system is also comparable to a 300K-word recognition system trained on the normal words. In the meantime, the decomposed system is much faster in terms of speed and also needs less memory than the systems with larger than 64K vocabularies |
Year | DOI | Venue |
|---|---|---|
2006 | 10.1109/ICASSP.2006.1660214 | ICASSP (1) |
Keywords | Field | DocType |
speech recognition,natural languages,word error rate,morphological decomposition,language training,large vocabulary arabic speech recognition,acoustic training data,word recognition system,arabic broadcast news transcription,out-of-vocabulary,acoustics,data mining,frequency,automatic speech recognition,word recognition,broadcasting,training data,dictionaries | Training set,Broadcasting,Arabic,Recognition system,Computer science,Word error rate,Compound,Speech recognition,Natural language,Artificial intelligence,Natural language processing,Vocabulary | Conference |
Volume | ISSN | ISBN |
1 | 1520-6149 | 1-4244-0469-X |
Citations | PageRank | References |
24 | 1.32 | 8 |
Authors | ||
5 | ||
Name | Order | Citations | PageRank |
|---|---|---|---|
| Bing Xiang | 1 | 1409 | 78.56 |
| Kham Nguyen | 2 | 47 | 3.64 |
| Long Nguyen | 3 | 326 | 84.60 |
| Richard M. Schwartz | 4 | 2839 | 717.76 |
| J. Makhoul | 5 | 1097 | 233.37 |