Publication Details

DNN Based Embeddings for Language Recognition

LOZANO DÍEZ, A.; PLCHOT, O.; MATĚJKA, P.; GONZALEZ-RODRIGUEZ, J. DNN Based Embeddings for Language Recognition. In Proceedings of ICASSP 2018. Calgary: IEEE Signal Processing Society, 2018. p. 5184-5188. ISBN: 978-1-5386-4658-8.
Czech title
DNN Embeddings pro rozpoznávání jazyka
Type
conference paper
Language
English
Authors
URL
Keywords

Embeddings, language recognition, LID, DNN

Abstract

In this work, we present a language identification (LID) system based on embeddings. In our case, an embedding is a fixed-length vector (similar to i-vector) that represents the whole utterance, but unlike i-vector it is designed to contain mostly information relevant to the target task (LID). In order to obtain these embeddings, we train a deep neural network (DNN) with sequence summarization layer to classify languages. In particular, we trained a DNN based on bidirectional long short-term memory (BLSTM) recurrent neural network (RNN) layers, whose frame-by-frame outputs are summarized into mean and standard deviation statistics. After this pooling layer, we add two fully connected layers whose outputs correspond to embeddings. Finally, we add a softmax output layer and train the whole network with multi-class cross-entropy objective to discriminate between languages. We report our results on NIST LRE 2015 and we compare the performance of embeddings and corresponding i-vectors both modeled by Gaussian Linear Classifier (GLC). Using only embeddings resulted in comparable performance to i-vectors and by performing score-level fusion we achieved 7.3% relative improvement over the baseline.

Published
2018
Pages
5184–5188
Proceedings
Proceedings of ICASSP 2018
ISBN
978-1-5386-4658-8
Publisher
IEEE Signal Processing Society
Place
Calgary
DOI
UT WoS
000446384605071
EID Scopus
BibTeX
@inproceedings{BUT155045,
  author="Alicia {Lozano Díez} and Oldřich {Plchot} and Pavel {Matějka} and Joaquin {Gonzalez-Rodriguez}",
  title="DNN Based Embeddings for Language Recognition",
  booktitle="Proceedings of ICASSP 2018",
  year="2018",
  pages="5184--5188",
  publisher="IEEE Signal Processing Society",
  address="Calgary",
  doi="10.1109/ICASSP.2018.8462403",
  isbn="978-1-5386-4658-8",
  url="https://www.fit.vut.cz/research/publication/11723/"
}
Back to top