1668

Harnessing graphics processors for the fast computation of acoustic likelihoods in speech recognition

Paul R. Dixon, Tasuku Oonishi, Sadaoki Furui
Department of Computer Science, Tokyo Institute of Technology, 2-12-1, Ookayama, Meguro-ku, Tokyo 152-8552, Japan
Computer Speech & Language, Vol. 23, No. 4. (October 2009), pp. 510-526

@article{dixon2009harnessing,

   title={Harnessing graphics processors for the fast computation of acoustic likelihoods in speech recognition},

   author={Dixon, P.R. and Oonishi, T. and Furui, S.},

   journal={Computer Speech & Language},

   volume={23},

   number={4},

   pages={510–526},

   issn={0885-2308},

   year={2009},

   publisher={Elsevier}

}

Source Source   

601

views

In large vocabulary continuous speech recognition (LVCSR) the acoustic model computations often account for the largest processing overhead. Our weighted finite state transducer (WFST) based decoding engine can utilize a commodity graphics processing unit (GPU) to perform the acoustic computations to move this burden off the main processor. In this paper we describe our new GPU scheme that can achieve a very substantial improvement in recognition speed whilst incurring no reduction in recognition accuracy. We evaluate the GPU technique on a large vocabulary spontaneous speech recognition task using a set of acoustic models with varying complexity and the results consistently show by using the GPU it is possible to reduce the recognition time with largest improvements occurring in systems with large numbers of Gaussians. For the systems which achieve the best accuracy we obtained between 2.5 and 3 times speed-ups. The faster decoding times translate to reductions in space, power and hardware costs by only requiring standard hardware that is already widely installed.
No votes yet.
Please wait...

* * *

* * *

HGPU group © 2010-2017 hgpu.org

All rights belong to the respective authors

Contact us: