Optimizing PLLR Features for Spoken Language Recognition
Mireia Díez, Amparo Varona, Mikel Peñagarikano, Luis Javier Rodríguez-Fuentes, Germán Bordel · 2014
Phone Log-Likelihood Ratios (PLLR) have been recently introduced as features for spoken language and speaker recognition systems. This representation has proven to be an effective way of retrieving acoustic-phonotactic information into frame-level vectors, which can be easily plugged into state-of-the-art systems. In a previous work, we began the search of reduced representations of PLLRs, as a mean of reducing computational costs. In this paper, we extend this search, by looking for the optimal compromise between feature vector size and system performance. Results achieved by Principal Component Analysis projection on the PLLR space are extensively analyzed. Also, to evaluate the effect of using larger temporal contexts, a Shifted Delta transformation is applied (and its optimal configuration explored) on highly reduced sets of PCA-projected PLLR features, leading to further performance improvements over the best PCA-projected PLLR set.