Phoneme recognition using Boosted Binary Features

Anindya Roy, Mathew Magimai.-Doss, Sebastien Marcel
2011 2011 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)  
In this paper, we propose a novel parts-based binary-valued feature for ASR. This feature is extracted using boosted ensembles of simple threshold-based classifiers. Each such classifier looks at a specific pair of time-frequency bins located on the spectro-temporal plane. These features termed as Boosted Binary Features (BBF) are integrated into standard HMM-based system by using multilayer perceptron (MLP) and single layer perceptron (SLP). Preliminary studies on TIMIT phoneme recognition
more » ... eme recognition task show that BBF yields similar or better performance compared to MFCC (67.8% accuracy for BBF vs. 66.3% accuracy for MFCC) using MLP, while it yields significantly better performance than MFCC (62.8% accuracy for BBF vs. 45.9% for MFCC) using SLP. This demonstrates the potential of the proposed feature for speech recognition.
doi:10.1109/icassp.2011.5947446 dblp:conf/icassp/RoyMM11 fatcat:k2pxzxrv7neyjbtnofqrjtjkjm