
Indexed in
License and use
Evaluation of an LSTM-RNN system in different NIST language recognition frameworks
Publicated to:The Speaker and Language Recognition Workshop. Odyssey 2016. 231-236 - 2016-01-01 (), DOI: 10.21437/Odyssey.2016-33
Authors: Zazo R; Lozano-Diez A; Gonzalez-Rodriguez J
Affiliations
Abstract
© Odyssey 2016: Speaker and Language Recognition Workshop. All rights reserved. Long Short-Term Memory recurrent neural networks (LSTM RNNs) provide an outstanding performance in language identification (LID) due to its ability to model speech sequences. So far, previously published LSTM RNNs solutions for LID deal with highly controlled scenarios, balanced datasets and limited channel variability. In this paper we evaluate an end-to-end LSTM LID system, comparing it against a classical i-vector system, on different environments based on data from Language Recognition Evaluations (LRE) organized by NIST. In order to analyze the behavior we train and test our system on a balanced and controlled subset of LRE09, on the develompent data of LRE15 and, finally, on the evaluation set of LRE15. Our results show that an end-to-end recurrent system clearly outperforms the reference i-vector system in a controlled environment, specially when dealing with short utterances. However, our deep learning approach is more sensitive to unbalanced datasets, channel variability and, specially, to the mismatch between development and test datasets.
Keywords
Quality index
Bibliometric impact. Analysis of the contribution and dissemination channel
Independientemente del impacto esperado determinado por el canal de difusión, es importante destacar el impacto real observado de la propia aportación.
Según las diferentes agencias de indexación, el número de citas acumuladas por esta publicación hasta la fecha 2025-07-29:
- Scopus: 12
Impact and social visibility
Leadership analysis of institutional authors
There is a significant leadership presence as some of the institution’s authors appear as the first or last signer, detailed as follows: First Author (ZAZO CANDIL, RUBEN) and Last Author (GONZALEZ RODRIGUEZ, JOAQUIN).