Using parallel architectures in speech recognition

/in , , /by
Using parallel architectures in speech recognition

Cardinal, Patrick and Dumouchel, Pierre and Boulianne, Gilles

Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH 2009

Abstract : The speed of modern processors has remained constant over the last few years and thus, to be scalable, applications must be parallelized. In addition to the main CPU, almost every computer is equipped with a Graphics Processors Unit (GPU) which is in essence a specialized parallel processor. This paper explores how performances of speech recognition systems can be enhanced by using GPU for the acoustic computations and multicore CPUs for the Viterbi search in a large vocabulary application. The multi-core implementation of our speech recognition system runs 1.3 times faster than the single-threaded CPU implementation. Addition of the GPU for dedicated acoustic computations increases the speed by a factor of 2.8, leading to a word accuracy improvement of 16.6% absolute at real-time, compared to the the single-threaded CPU implementation. Copyright © 2009 ISCA.

You might also like
Learning global-local distance metrics for signature-based biometric cryptosystems
Incremental boolean combination of classifiers
Automatic genre classification of music content
Deep interpretable classification and weakly-supervised segmentation of histology images via max-min uncertainty
A method for dynamic ensemble selection based on a filter and an adaptive distance to improve the quality of the regions of competence
Vérification de signatures manuscrites par modèles déformables
Impact of watermarking on offline signature verification in intelligent bio-watermarking systems
Non-parametric Uni-modality Constraints for Deep Ordinal Classification