Title | ||
---|---|---|
Round-robin duel discriminative language models in one-pass decoding with on-the-fly error correction |
Abstract | ||
---|---|---|
This paper focuses on discriminative n-gram language models for large vocabulary speech recognition. We have proposed a novel training method called the round-robin duel discrimination (R2D2) method. Our previous report showed that R2D2 outperforms conventional methods on word n-gram based discriminative language models (DLMs). In this paper, we achieve additional error reduction and one-pass decoding at the same time. The keys to achieving this are the use of morphological features and the on-the-fly composition of weighted finite-state transducers (WFSTs) that represent both word and morphological discriminative features. Our experimental results show that R2D2 can reduce recognition errors more effectively than conventional methods in the reranking of n-best hypotheses and one-pass decoding can be accomplished with an equivalent accuracy. |
Year | DOI | Venue |
---|---|---|
2011 | 10.1109/ICASSP.2011.5947626 | Acoustics, Speech and Signal Processing |
Keywords | Field | DocType |
error correction codes,speech coding,speech recognition,DLM,R2D2 method,WFST,discriminative n-gram language models,large vocabulary speech recognition,on-the-fly error correction,one-pass decoding,round-robin duel discriminative language models,weighted finite-state transducers,Discriminative language model,Error correction,On-the-fly algorithm,R2D2,WFST | Vocabulary speech recognition,Speech coding,Pattern recognition,Computer science,On the fly,Error detection and correction,Speech recognition,Artificial intelligence,Decoding methods,Hidden Markov model,Discriminative model,Language model | Conference |
ISSN | ISBN | Citations |
1520-6149 E-ISBN : 978-1-4577-0537-3 | 978-1-4577-0537-3 | 1 |
PageRank | References | Authors |
0.35 | 10 | 4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Takanobu Oba | 1 | 53 | 12.09 |
Takaaki Hori | 2 | 408 | 45.58 |
Akinori Ito | 3 | 272 | 62.32 |
Atsushi Nakamura | 4 | 108 | 12.67 |