Incorporation of Language Discriminative Information into Recurrent Neural Networks Models to LID Tasks

Abstract

Language Identification (LID) is an essential research topic in the Automatic Recognition Speech area. One of the most important characteristics relative to language is context information. In this article, considering a phonotactic approach where the phonetic units called “phone-grams” are used, in order to introduce such context information, a novel technique is proposed. Language discriminative information has been incorporated in the Recurrent Neural Network Language Models generation (RNNLMs) in the weights initialization stage to improve the Language Identification task. This technique has been evaluated using KALAKA-3 database that contains 108 h of audios of six languages to be recognized. The metric used in this work has been the Average Detection Cost metric Cavg. In relation to the phonetic units called “phone-grams” used in order to incorporate context information in the features used to train the RNNLM, it has been considered phone-grams of two elements “2phone-grams” and three elements “3phone-grams”, obtaining a relative improvement up to 17% and 15,44% respectively compared to the results obtaining using RNNLMs.