Ebooks

Speech Recognition using Neural Networks (Brain Study)

  • Download 5x Faster
  • Download torrent
  • Direct Download
  • Rate this torrent +  |  -
Speech Recognition using Neural Networks (Brain Study)

Anonymous and Direct Download 300GB+ free


Torrent info

Name:Speech Recognition using Neural Networks (Brain Study)

Total Size: 970.74 KB

Magnet: Magnet Link

Seeds: 1

Leechers: 0

Stream: Watch Online @ Movie4u

Last Updated: 2010-09-18 06:49:02 (Update Now)

Torrent added: 2008-08-27 15:48:03




Torrent Files List


(Brain Study)Speech Recognition using Neural Networks.PDF (Size: 970.74 KB) (Files: 1)

 (Brain Study)Speech Recognition using Neural Networks.PDF

970.74 KB
 

Announce URL: http://www.ebookvortex.com/announce.php

Torrent description

This paper is submitted in fulfilment of the requirements for
a degree of Doctor of Philosophy in Computer Science by Joe Tebelskis to School of Computer Science
Carnegie Mellon University
Pittsburgh, Pennsylvania

This thesis examines how artificial neural networks can benefit a large vocabulary, speaker
independent, continuous speech recognition system. Currently, most speech recognition
systems are based on hidden Markov models (HMMs), a statistical framework that supports
both acoustic and temporal modeling. Despite their state-of-the-art performance, HMMs
make a number of suboptimal modeling assumptions that limit their potential effectiveness.
Neural networks avoid many of these assumptions, while they can also learn complex functions,
generalize effectively, tolerate noise, and support parallelism. While neural networks
can readily be applied to acoustic modeling, it is not yet clear how they can be used for temporal
modeling. Therefore, we explore a class of systems called NN-HMM hybrids, in which
neural networks perform acoustic modeling, and HMMs perform temporal modeling. We
argue that a NN-HMM hybrid has several theoretical advantages over a pure HMM system,
including better acoustic modeling accuracy, better context sensitivity, more natural discrimination,
and a more economical use of parameters. These advantages are confirmed
experimentally by a NN-HMM hybrid that we developed, based on context-independent
phoneme models, that achieved 90.5% word accuracy on the Resource Management database,
in contrast to only 86.0% accuracy achieved by a pure HMM under similar conditions.

related torrents

Torrent name

health leech seeds Size
 


comments (0)

Main Menu