Phoneme Recognition Using Neural Network and Sequence Learning Model

Phoneme Recognition Using Neural Network and Sequence Learning Model

Bibliographic Details
Main Author: Huang, Yiming
Language:English
Published: Ohio University / OhioLINK 2009
Subjects:
Artificial Intelligence
Design
Electrical Engineering
Engineering
Phoneme Recognition
Neural Network
Long-Term Memory
Sequence Learning
Online Access:http://rave.ohiolink.edu/etdc/view?acc_num=ohiou1236027180
id ndltd-OhioLink-oai-etd.ohiolink.edu-ohiou1236027180
record_format oai_dc
spelling ndltd-OhioLink-oai-etd.ohiolink.edu-ohiou12360271802021-08-03T05:45:57Z Phoneme Recognition Using Neural Network and Sequence Learning Model Huang, Yiming Artificial Intelligence Design Electrical Engineering Engineering Phoneme Recognition Neural Network Long-Term Memory Sequence Learning <p>The purpose of this thesis is to describe a biologically motivated approach for phoneme recognition by using a self-organized neural network and sequence learning algorithm. Phoneme recognition in continuous speech is a tough task with a low accuracy rate. By using the sequence learning algorithm to add sequential information of individual phonemes, recognition performance can be improved.</p><p>This thesis includes three parts. A self-organized neural network is the first stage, which classifies the input sound waves into forty two different phoneme categories. The 42 output neurons of the neural network are sent to the Sequence Learning block which is composed of Long Term Memory cells. Finally each LTM cell sends a unique feedback strength signal to each output of the neural network to predict the next phoneme, hence, to improve the phoneme recognition based on the sequential information.</p> 2009-04-27 English text Ohio University / OhioLINK http://rave.ohiolink.edu/etdc/view?acc_num=ohiou1236027180 http://rave.ohiolink.edu/etdc/view?acc_num=ohiou1236027180 unrestricted This thesis or dissertation is protected by copyright: all rights reserved. It may not be copied or redistributed beyond the terms of applicable copyright laws.
collection NDLTD
language English
sources NDLTD
topic Artificial Intelligence
Design
Electrical Engineering
Engineering
Phoneme Recognition
Neural Network
Long-Term Memory
Sequence Learning
spellingShingle Artificial Intelligence
Design
Electrical Engineering
Engineering
Phoneme Recognition
Neural Network
Long-Term Memory
Sequence Learning
Huang, Yiming
Phoneme Recognition Using Neural Network and Sequence Learning Model
author Huang, Yiming
author_facet Huang, Yiming
author_sort Huang, Yiming
title Phoneme Recognition Using Neural Network and Sequence Learning Model
title_short Phoneme Recognition Using Neural Network and Sequence Learning Model
title_full Phoneme Recognition Using Neural Network and Sequence Learning Model
title_fullStr Phoneme Recognition Using Neural Network and Sequence Learning Model
title_full_unstemmed Phoneme Recognition Using Neural Network and Sequence Learning Model
title_sort phoneme recognition using neural network and sequence learning model
publisher Ohio University / OhioLINK
publishDate 2009
url http://rave.ohiolink.edu/etdc/view?acc_num=ohiou1236027180
work_keys_str_mv AT huangyiming phonemerecognitionusingneuralnetworkandsequencelearningmodel
_version_ 1719424934444269568

Similar Items