Time normalization of LPC feature using warping method
This paper presents pre-processing of input features to artificial neural network (NN). This is for preparation of reliable reference templates for the set of words to be recognized. The processed features are pitch and Linear Predictive Coefficients (LPC) for input and reference templates, based on...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | en |
| Published: |
Faculty of Electrical Engineering, Universiti Teknologi Malaysia
2005
|
| Subjects: | |
| Online Access: | http://eprints.utm.my/1308/1/Elektrika05.pdf http://eprints.utm.my/1308/ http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.631.3507 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1845470441451290624 |
|---|---|
| author | Sudirman, Rubita Salleh, Sh. Hussain Khalid, Puspa Inayat Ahmad, Abd. Hamid |
| author_facet | Sudirman, Rubita Salleh, Sh. Hussain Khalid, Puspa Inayat Ahmad, Abd. Hamid |
| author_sort | Sudirman, Rubita |
| building | UTM Library |
| collection | Institutional Repository |
| content_provider | Universiti Teknologi Malaysia |
| content_source | UTM Institutional Repository |
| continent | Asia |
| country | Malaysia |
| description | This paper presents pre-processing of input features to artificial neural network (NN). This is for preparation of reliable reference templates for the set of words to be recognized. The processed features are pitch and Linear Predictive Coefficients (LPC) for input and reference templates, based on Dynamic Time Warping (DTW) algorithm. The first task is to extract pitch features using Pitch Scale Harmonic Filter (PSHF) algorithm. Another task is to align the input frames (test set) to the reference template (training set) using DTW fixing frame (DTW-FF) algorithm. This proper time normalization is needed since NN is designed to compare data of the same length whilst same speech can varies in their length. By doing frame fixing (time normalization), the test set and the training set is adjusted to the same number of frames. Having both pitch and LPC features fixed frames, speech recognition using neural network can be performed. |
| format | Article |
| id | my.utm.eprints-1308 |
| institution | Universiti Teknologi Malaysia |
| language | en |
| publishDate | 2005 |
| publisher | Faculty of Electrical Engineering, Universiti Teknologi Malaysia |
| record_format | eprints |
| spelling | my.utm.eprints-13082017-04-10T04:32:10Z http://eprints.utm.my/1308/ Time normalization of LPC feature using warping method Sudirman, Rubita Salleh, Sh. Hussain Khalid, Puspa Inayat Ahmad, Abd. Hamid T Technology (General) This paper presents pre-processing of input features to artificial neural network (NN). This is for preparation of reliable reference templates for the set of words to be recognized. The processed features are pitch and Linear Predictive Coefficients (LPC) for input and reference templates, based on Dynamic Time Warping (DTW) algorithm. The first task is to extract pitch features using Pitch Scale Harmonic Filter (PSHF) algorithm. Another task is to align the input frames (test set) to the reference template (training set) using DTW fixing frame (DTW-FF) algorithm. This proper time normalization is needed since NN is designed to compare data of the same length whilst same speech can varies in their length. By doing frame fixing (time normalization), the test set and the training set is adjusted to the same number of frames. Having both pitch and LPC features fixed frames, speech recognition using neural network can be performed. Faculty of Electrical Engineering, Universiti Teknologi Malaysia 2005-12 Article NonPeerReviewed application/pdf en http://eprints.utm.my/1308/1/Elektrika05.pdf Sudirman, Rubita and Salleh, Sh. Hussain and Khalid, Puspa Inayat and Ahmad, Abd. Hamid (2005) Time normalization of LPC feature using warping method. Elektrika, 7 (2). pp. 29-35. ISSN 0128-4428 http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.631.3507 |
| spellingShingle | T Technology (General) Sudirman, Rubita Salleh, Sh. Hussain Khalid, Puspa Inayat Ahmad, Abd. Hamid Time normalization of LPC feature using warping method |
| title | Time normalization of LPC feature using warping method |
| title_full | Time normalization of LPC feature using warping method |
| title_fullStr | Time normalization of LPC feature using warping method |
| title_full_unstemmed | Time normalization of LPC feature using warping method |
| title_short | Time normalization of LPC feature using warping method |
| title_sort | time normalization of lpc feature using warping method |
| topic | T Technology (General) |
| url | http://eprints.utm.my/1308/1/Elektrika05.pdf http://eprints.utm.my/1308/ http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.631.3507 |
| url_provider | http://eprints.utm.my/ |