Development of isolated Malay words speech recognition prototype using recurrent neural network / Irdhan Sarbini
In this research, a prototype of isolated Malay word speech recognition using recurrent neural network (RNN) is proposed. The research is working on speaker independent, which is combination of male and female respondent. A simple three-layer RNN which is Elman Network is employed to learn the pa...
Saved in:
| Main Author: | |
|---|---|
| Format: | Thesis |
| Language: | English |
| Published: |
2005
|
| Online Access: | http://ir.uitm.edu.my/id/eprint/1496/1/TD_IRDHAN%20SARBINI%20CS%2005_5.pdf http://ir.uitm.edu.my/id/eprint/1496/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| id |
my.uitm.ir.1496 |
|---|---|
| record_format |
eprints |
| spelling |
my.uitm.ir.14962017-05-30T07:32:33Z http://ir.uitm.edu.my/id/eprint/1496/ Development of isolated Malay words speech recognition prototype using recurrent neural network / Irdhan Sarbini Sarbini, Irdhan In this research, a prototype of isolated Malay word speech recognition using recurrent neural network (RNN) is proposed. The research is working on speaker independent, which is combination of male and female respondent. A simple three-layer RNN which is Elman Network is employed to learn the pattern of speech features. Melfrequency Cepstral Coefficient (MFCC) feature is selected and the features are extracted by using Speech Filing System freeware application. Experiments are performed to determine the optimal number of hidden neurons for the architecture of RNN. The total recognition rate is 95 %. This research also reveals that RNN is able to give good performance for speech recognition and for incomplete data. 2005 Thesis NonPeerReviewed text en http://ir.uitm.edu.my/id/eprint/1496/1/TD_IRDHAN%20SARBINI%20CS%2005_5.pdf Sarbini, Irdhan (2005) Development of isolated Malay words speech recognition prototype using recurrent neural network / Irdhan Sarbini. Degree thesis, Universiti Teknologi MARA. |
| institution |
Universiti Teknologi Mara |
| building |
Tun Abdul Razak Library |
| collection |
Institutional Repository |
| continent |
Asia |
| country |
Malaysia |
| content_provider |
Universiti Teknologi Mara |
| content_source |
UiTM Institutional Repository |
| url_provider |
http://ir.uitm.edu.my/ |
| language |
English |
| description |
In this research, a prototype of isolated Malay word speech recognition using
recurrent neural network (RNN) is proposed. The research is working on speaker
independent, which is combination of male and female respondent. A simple three-layer
RNN which is Elman Network is employed to learn the pattern of speech features. Melfrequency
Cepstral Coefficient (MFCC) feature is selected and the features are extracted
by using Speech Filing System freeware application. Experiments are performed to
determine the optimal number of hidden neurons for the architecture of RNN. The total
recognition rate is 95 %. This research also reveals that RNN is able to give good
performance for speech recognition and for incomplete data. |
| format |
Thesis |
| author |
Sarbini, Irdhan |
| spellingShingle |
Sarbini, Irdhan Development of isolated Malay words speech recognition prototype using recurrent neural network / Irdhan Sarbini |
| author_facet |
Sarbini, Irdhan |
| author_sort |
Sarbini, Irdhan |
| title |
Development of isolated Malay words speech recognition prototype using recurrent neural network / Irdhan Sarbini |
| title_short |
Development of isolated Malay words speech recognition prototype using recurrent neural network / Irdhan Sarbini |
| title_full |
Development of isolated Malay words speech recognition prototype using recurrent neural network / Irdhan Sarbini |
| title_fullStr |
Development of isolated Malay words speech recognition prototype using recurrent neural network / Irdhan Sarbini |
| title_full_unstemmed |
Development of isolated Malay words speech recognition prototype using recurrent neural network / Irdhan Sarbini |
| title_sort |
development of isolated malay words speech recognition prototype using recurrent neural network / irdhan sarbini |
| publishDate |
2005 |
| url |
http://ir.uitm.edu.my/id/eprint/1496/1/TD_IRDHAN%20SARBINI%20CS%2005_5.pdf http://ir.uitm.edu.my/id/eprint/1496/ |
| _version_ |
1685648150043295744 |
| score |
13.214268 |