Skip to main content

LID-senones and their statistics for language identification

Jin, Ma, Song, Yan, McLoughlin, Ian Vince, Dai, Li-Rong (2017) LID-senones and their statistics for language identification. Ieee Transactions On Audio Speech And Language Processing, 26 (1). pp. 171-183. ISSN 1558-7916. E-ISSN 2329-9304. (doi:10.1109/TASLP.2017.2766023) (KAR id:64034)

PDF Publisher pdf
Language: English


Creative Commons Licence
This work is licensed under a Creative Commons Attribution 4.0 International License.
Download (2MB) Preview
[img]
Preview
PDF Author's Accepted Manuscript
Language: English

Restricted to Repository staff only
Contact us about this Publication
[img]
Official URL
http://dx.doi.org/10.1109/TASLP.2017.2766023

Abstract

Recent research on end-to-end training structures for language identification has raised the possibility that intermediate language-sensitive feature units exist which are analogous to phonetically-sensitive senones in automatic speech recognition systems. Termed LID (language identification)-senones, the statistics derived from these feature units have been shown to be beneficial in discriminating between languages, particularly for short utterances. This paper examines the evidence for the existence of LID-senones before designing and evaluating LID systems based on low and high level statistics of LID-senones with both generative and discriminative models. For the standard NIST LRE 2009 task on 23 languages, LID-senone based systems are shown to outperform state-of-the art DNN/i-vector methods both when LID-senones are used directly for classification and when LID-senone statistics are used for i-vector formation.

Item Type: Article
DOI/Identification number: 10.1109/TASLP.2017.2766023
Uncontrolled keywords: Language identification, Deep neural networks, i-vector, LID-senones
Subjects: T Technology
Divisions: Faculties > Sciences > School of Computing > Data Science
Depositing User: Ian McLoughlin
Date Deposited: 16 Oct 2017 13:13 UTC
Last Modified: 29 May 2019 19:42 UTC
Resource URI: https://kar.kent.ac.uk/id/eprint/64034 (The current URI for this page, for reference purposes)
McLoughlin, Ian Vince: https://orcid.org/0000-0001-7111-2008
  • Depositors only (login required):

Downloads

Downloads per month over past year