Optimization of the Gaussian Mixture Model Evaluation on GPU
The result's identifiers
Result code in IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F49777513%3A23520%2F11%3A43898500" target="_blank" >RIV/49777513:23520/11:43898500 - isvavai.cz</a>
Result on the web
—
DOI - Digital Object Identifier
—
Alternative languages
Result language
angličtina
Original language name
Optimization of the Gaussian Mixture Model Evaluation on GPU
Original language description
In this paper we present a highly optimized implementation of Gaussian mixture acoustic model evaluation algorithm. Evaluation of these likelihoods is one of the~most computationally intensive parts of automatics speech recognizers but it can be well-parallelized and offloaded to GPU devices. Our approach offers significant speed-up compared to the recently published approaches, since it exploits the GPU architecture better. All the recent implementations were programmed either in CUDA or OpenCL GPU programming frameworks. We present results for both; CUDA as well as OpenCL. Results suggest that even very large acoustic models can be utilized in real-time speech recognition engines on computers and laptops equipped with a low-end GPU. Optimization of acoustic likelihoods computation on GPU enables to use the remaining GPU resources for offloading of other compute-intensive parts of LVCSR decoder.
Czech name
—
Czech description
—
Classification
Type
D - Article in proceedings
CEP classification
JD - Use of computers, robotics and its application
OECD FORD branch
—
Result continuities
Project
Result was created during the realization of more than one project. More information in the Projects tab.
Continuities
P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)<br>S - Specificky vyzkum na vysokych skolach
Others
Publication year
2011
Confidentiality
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů
Data specific for result type
Article name in the collection
12th Annual Conference of the International Speech Communication Association 2011 (INTERSPEECH 2011)
ISBN
978-1-61839-270-1
ISSN
1990-9772
e-ISSN
—
Number of pages
4
Pages from-to
1748-1751
Publisher name
Curran Associates, Inc.
Place of publication
Red Hook, NY 12571, USA
Event location
Florencie, Itálie
Event date
Aug 28, 2011
Type of event by nationality
WRD - Celosvětová akce
UT code for WoS article
—