|
Abstract
|
|
|---|---|
| New advances in Language Identification (LID) using Recurrent Neural Networks (RNNs) and Neural Embeddings have been proposed recently. While their application has been successfully applied at a word level, results at a phoneme level may not be as good because of the greater variability found in phoneme sequences which reduces LID accuracy. Thus, we propose to use phonetic units called ?phone-grams? that implicitly include longer-context information and use them to train neural embeddings and RNN language models (RNNLMs). Neural embeddings are used in a pre-processing data phase to reduce the scattering problem produced by the high number of resulting phone-gram units, and, in a second phase, we have used the RNNLMs to obtain the scores of each language in the identification task following a PPRLM structure. Results in terms of Cavg on the KALAKA-3 database show that the use of phone-grams provides up to 14.4% relative improvement over a baseline using only phonemes as features. In addition, our proposed strategy of reducing the number of phone-gram units using neural embeddings contributes to obtain up to 23.0% relative improvement. Finally, fusing the best system with MFCC-based acoustic i-vectors and a traditional PPRLM architecture provides up to 39.3% improvement. | |
|
International
|
Si |
|
JCR
|
Si |
|
Title
|
Ieee Latin America Transactions |
|
ISBN
|
1548-0992 |
|
Impact factor JCR
|
0,502 |
|
Impact info
|
Datos JCR del año 2016 |
|
Volume
|
16 |
|
|
|
|
Journal number
|
7 |
|
From page
|
2033 |
|
To page
|
2039 |
|
Month
|
JULIO |
|
Ranking
|
Journal Rank in Category 239/260 |