Full metadata record
DC poleHodnotaJazyk
dc.contributor.authorVaněk, Jan
dc.contributor.authorTrmal, Jan
dc.contributor.authorPsutka, Josef V.
dc.contributor.authorPsutka, Josef
dc.date.accessioned2015-12-11T08:03:03Z
dc.date.available2015-12-11T08:03:03Z
dc.date.issued2011
dc.identifier.citationVANĚK, Jan; TRMAL, Jan; PSUTKA, Josef V.; PSUTKA, Josef. Optimization of the Gaussian mixture model evaluation on GPU. In: Proceedings of ICSPL 2011: 12th Annual Conference of the International Speech Communication Association 2011, Firenze, Italy, 27-31 August 2011. [Baixas]: ISCA, 2011, p. 1748-1751. ISSN 1990-9772.en
dc.identifier.isbn978-1-61839-270-1
dc.identifier.issn1990-9772
dc.identifier.urihttp://hdl.handle.net/11025/16962
dc.identifier.urihttp://www.kky.zcu.cz/cs/publications/VanekJ_2011_Optimizationofthe
dc.format4 s.cs
dc.format.mimetypeapplication/pdf
dc.language.isoenen
dc.publisherISCAcs
dc.rights© Jan Vaněk - Jan Trmal - Josef V. Psutka - Josef Psutkacs
dc.subjectCUDAcs
dc.subjectGPUcs
dc.subjectOpenCLcs
dc.subjectsměsi Gaussovských modelůcs
dc.titleOptimization of the Gaussian mixture model evaluation on GPUen
dc.title.alternativeOptimalizovaný výpočet směsí normálních rozložení na GPUcs
dc.typečlánekcs
dc.typearticleen
dc.rights.accessopenAccessen
dc.type.versionpublishedVersionen
dc.description.abstract-translatedIn 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 computeintensive parts of LVCSR decoder. Other possible use of the freed GPU resources is to evaluate several acoustic models at the same time and use fusion techniques or model selection techniques to improve the quality of resulting conditional likelihoods under diverse conditions.en
dc.subject.translatedCUDAen
dc.subject.translatedGPUen
dc.subject.translatedOpenCLen
dc.subject.translatedGaussian mixture modelsen
dc.type.statusPeer-revieweden
Vyskytuje se v kolekcích:Články / Articles (KIV)
Články / Articles (KKY)

Soubory připojené k záznamu:
Soubor Popis VelikostFormát 
VanekJ_2011_Optimizationofthe.pdfPlný text226,25 kBAdobe PDFZobrazit/otevřít
Zobrazit minimální záznam Zobrazit statistiky


Použijte tento identifikátor k citaci nebo jako odkaz na tento záznam: http://hdl.handle.net/11025/16962

Všechny záznamy v DSpace jsou chráněny autorskými právy, všechna práva vyhrazena.

hledání
navigace
  1. DSpace at University of West Bohemia
  2. Publikační činnost / Publications
  3. Fakulta aplikovaných věd / Faculty of Applied Sciences
  4. Katedra kybernetiky / Department of Cybernetics
  5. Články / Articles (KKY)