Full metadata record
DC poleHodnotaJazyk
dc.contributor.authorVaněk, Jan
dc.contributor.authorTrmal, Jan
dc.contributor.authorPsutka, Josef V.
dc.contributor.authorPsutka, Josef
dc.date.accessioned2016-01-07T12:29:44Z
dc.date.available2016-01-07T12:29:44Z
dc.date.issued2012
dc.identifier.citationVANĚK, Jan; TRMAL, Jan; PSUTKA, Josef V.; PSUTKA, Josef. Optimized acoustic likelihoods computation for NVIDIA and ATI/AMD graphics processors. In: Audio, speech, and language processing, 20, 6, p. 1818-1828. ISSN 1558-7916.en
dc.identifier.issn1558-7916
dc.identifier.urihttp://www.kky.zcu.cz/cs/publications/JanVanek_2012_OptimizedAcoustic
dc.identifier.urihttp://hdl.handle.net/11025/17163
dc.format11 s.cs
dc.format.mimetypeapplication/pdf
dc.language.isoenen
dc.publisherIEEE Pressen
dc.rights© Jan Vaněk - Jan Trmal - Josef V. Psutka - Josef Psutkacs
dc.subjectautomatické rozpoznávání řečics
dc.subjectparalelní algoritmuscs
dc.subjectparalelní architekturycs
dc.subjectvýkon softwarucs
dc.titleOptimized acoustic likelihoods computation for NVIDIA and ATI/AMD graphics processorsen
dc.typečlánekcs
dc.typearticleen
dc.rights.accessopenAccessen
dc.type.versionpublishedVersionen
dc.description.abstract-translatedIn this paper, we describe an optimized version of a Gaussian-mixture-based acoustic model likelihood evaluation algorithm for graphical processing units (GPUs). The evaluation of these likelihoods is one of the most computationally intensive parts of automatic speech recognizers, but it can be parallelized and offloaded to GPU devices. Our approach offers a significant speed-up over the recently published approaches, because it utilizes the GPU architecture in a more effective manner. All the recent implementations have been intended only for NVIDIA graphics processors, programmed either in CUDA or OpenCL GPU programming frameworks. We present results for both CUDA and OpenCL. Further, we have developed an OpenCL implementation optimized for ATI/AMD GPUs. Results suggest that even very large acoustic models can be used in real-time speech recognition engines on computers equipped with a low-end GPU or laptops. In addition, the completely asynchronous GPU management provides additional CPU resources for the decoder part of the LVCSR. The optimized implementation enables us to apply fusion techniques together with evaluating many (10 or even more) speaker-specific acoustic models. We apply this technique to a real-time parliamentary speech recognition system where the speaker changes frequently.en
dc.subject.translatedautomatic speech recognitionen
dc.subject.translatedparallel algorithmsen
dc.subject.translatedparallel architecturesen
dc.subject.translatedsoftware performanceen
dc.identifier.doi10.1109/TASL.2012.2190928
dc.type.statusPeer-revieweden
Vyskytuje se v kolekcích:Články / Articles (KIV)
Články / Articles (KKY)

Soubory připojené k záznamu:
Soubor Popis VelikostFormát 
JanVanek_2012_OptimizedAcoustic.pdfPlný text614,01 kBAdobe PDFZobrazit/otevřít
Zobrazit minimální záznam Zobrazit statistiky


Použijte tento identifikátor k citaci nebo jako odkaz na tento záznam: http://hdl.handle.net/11025/17163

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)