Characterization of Speech Recognition Systems on GPU Architectures

This master thesis characterizes the performance and energy bottlenecks of speech recognition systems when running on modern GPU, with the aim of providing useful information for designing future GPU architectures, as well as proposing a GPU configuration more well-suited for speech recognition.

Bibliographic Details
Author: Segura Salvador, Albert|||0000-0001-5084-9246
Format: master thesis
Publication Date:2016
Country:España
Institution:Universitat Politècnica de Catalunya (UPC)
Repository:UPCommons. Portal del coneixement obert de la UPC
Language:English
OAI Identifier:oai:upcommons.upc.edu:2117/89884
Online Access:https://hdl.handle.net/2117/89884
Access Level:Open access
Keyword:Automatic speech recognition
Reconeixement de veu
Viterbi
Kaldi
GPU
GPGPU-Sim.
Speech recognition
Reconeixement automàtic de la parla
Àrees temàtiques de la UPC::Informàtica
Description
Summary:This master thesis characterizes the performance and energy bottlenecks of speech recognition systems when running on modern GPU, with the aim of providing useful information for designing future GPU architectures, as well as proposing a GPU configuration more well-suited for speech recognition.