On the use of phone-gram units in recurrent neural networks for language identification

Christian Salamea, Luis Fernando D'Haro, Ricardo De Córdoba, Rubén San-Segundo

Research output: Contribution to conferencePaperpeer-review

Abstract

In this paper we present our results on using RNN-based LM scores trained on different phone-gram orders and using different phonetic ASR recognizers. In order to avoid data sparseness problems and to reduce the vocabulary of all possible n-gram combinations, a K-means clustering procedure was performed using phone-vector embeddings as a pre-processing step. Additional experiments to optimize the amount of classes, batch-size, hidden neurons, state-unfolding, are also presented. We have worked with the KALAKA-3 database for the plenty-closed condition [1]. Thanks to our clustering technique and the combination of high level phone-grams, our phonotactic system performs ~13% better than the unigram-based RNNLM system. Also, the obtained RNNLM scores are calibrated and fused with other scores from an acoustic-based i-vector system and a traditional PPRLM system. This fusion provides additional improvements showing that they provide complementary information to the LID system.

Original languageEnglish
Pages117-123
Number of pages7
DOIs
StatePublished - 1 Jan 2016
EventSpeaker and Language Recognition Workshop, Odyssey 2016 - Bilbao, Spain
Duration: 21 Jun 201624 Jun 2016

Conference

ConferenceSpeaker and Language Recognition Workshop, Odyssey 2016
CountrySpain
CityBilbao
Period21/06/1624/06/16

Fingerprint Dive into the research topics of 'On the use of phone-gram units in recurrent neural networks for language identification'. Together they form a unique fingerprint.

Cite this