DocumentCode :
179522
Title :
Automatic language identification using deep neural networks
Author :
Lopez-Moreno, Ignacio ; Gonzalez-Dominguez, Jorge ; Plchot, Oldrich ; Martinez, D. ; Gonzalez-Rodriguez, Joaquin ; Moreno, Pablo
Author_Institution :
Google Inc., New York, NY, USA
fYear :
2014
fDate :
4-9 May 2014
Firstpage :
5337
Lastpage :
5341
Abstract :
This work studies the use of deep neural networks (DNNs) to address automatic language identification (LID). Motivated by their recent success in acoustic modelling, we adapt DNNs to the problem of identifying the language of a given spoken utterance from short-term acoustic features. The proposed approach is compared to state-of-the-art i-vector based acoustic systems on two different datasets: Google 5M LID corpus and NIST LRE 2009. Results show how LID can largely benefit from using DNNs, especially when a large amount of training data is available. We found relative improvements up to 70%, in Cavg, over the baseline system.
Keywords :
natural languages; neural nets; speech recognition; vectors; DNN; Google 5M LID corpus; I-vector based acoustic systems; NIST LRE 2009; automatic language identification; deep neural networks; short-term acoustic features; Acoustics; Google; NIST; Neural networks; Speech; Speech recognition; Training; Automatic Language Identification; DNNs; i-vectors;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Acoustics, Speech and Signal Processing (ICASSP), 2014 IEEE International Conference on
Conference_Location :
Florence
Type :
conf
DOI :
10.1109/ICASSP.2014.6854622
Filename :
6854622
Link To Document :
بازگشت