Speech Recognition using Neural Networks (Brain Study)

[ Download options ] alternative direct download for Speech Recognition using Neural Networks (Brain Study) from usenet with usenext client 5x faster.
Usenet was created before the internet and consists of more than 60000 boards for discussions (newsgroups).
Opinions are exchanged in these boards.There is nothing you won't find there... or download torrent.
Before download check the report, the internal files and the comments of this torrent.



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.

Download this torrent or use Magnet Link	Add to your bookmarks
Speech Recognition using Neural Networks (Brain Study).torrent
↓ Alternative Direct Download FREE 5x FASTER. Click here to download the usenext client.