A multiple-Gaussian classifier for Language Identification using acoustic information and PPRLM scores
Ricardo de Córdoba, Rubén San-Segundo, Javier Macías-Guarasa, Fernando Fernández-Martínez · 2006
We present several innovative techniques that can be applied in a PPRLM system for language identification (LID), obtaining a 61.8 % relative error reduction from our base system. First, the application of a variable threshold in score computation, dependent on the average scores in the language model, provided a 35 % error reduction. A random selection of sentences for the different sets and the use of silence models also improved the system. Then, to improve the classifier, we compared the bias removal technique (up to 19 % error reduction) and a Gaussian classifier (up to 37 % error reduction). Then, we included the acoustic score in the Gaussian classifier (2 % error reduction) and increased the number of Gaussians to have a multiple-Gaussian classifier (14 % error reduction). Finally, we included additional acoustic HMMs of the same language with success (18 % relative improvement). We will show how all these improvements have been mostly additive. 1.