Methods for Spoken Language Identification

Abstract

In this paper, we explore several machine learning techniques for classifying spoken language. In particular, we construct algorithms which utilize various spectral features derived from English and Mandarin Chinese phone call audio to predict the language to which the phone call belongs. We investigate multiple feature sets and modeling approaches, and find that Gaussian Mixture Models, combined with shifted delta cepstra (SDC) features, achieve the best performance.

Tasks

Reproductions