Optimization of the Gaussian Mixture Model Evaluation on GPU

  title={Optimization of the Gaussian Mixture Model Evaluation on GPU},
  author={Jan Vanek and Jan Trmal and Josef V. Psutka and Josef Psutka},
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… CONTINUE READING
8 Citations
8 References
Similar Papers

Similar Papers

Loading similar papers…