Development of language identification using line spectral frequencies and learning vector quantization networks
Language identification system has become a very active research nowadays due to the need of intercultural human communication. This paper proposed a Language Identification System using Line Spectral Frequencies (LSF) and Linear Vector Quantization (LVQ) network. LSF was used due to its robustness...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English English |
| Published: |
Faculty of Electronic and Computer Engineering, Universiti Teknikal Malaysia Melaka.
2017
|
| Subjects: | |
| Online Access: | http://irep.iium.edu.my/61180/ http://irep.iium.edu.my/61180/ http://irep.iium.edu.my/61180/1/GunawanLanguageIdentification_JTEC_3060-8256-1-SM_Dec2017.pdf http://irep.iium.edu.my/61180/7/61180_Development%20of%20language%20identification%20using%20line_SCOPUS.pdf |
| id |
iium-61180 |
|---|---|
| recordtype |
eprints |
| spelling |
iium-611802018-04-18T02:57:41Z http://irep.iium.edu.my/61180/ Development of language identification using line spectral frequencies and learning vector quantization networks Gunawan, Teddy Surya Kartiwi, Mira Ardzemi, Nor Hazima TK Electrical engineering. Electronics Nuclear engineering Language identification system has become a very active research nowadays due to the need of intercultural human communication. This paper proposed a Language Identification System using Line Spectral Frequencies (LSF) and Linear Vector Quantization (LVQ) network. LSF was used due to its robustness compared to normal linear predictor coefficients (LPC), while LVQ was used due to its low complexity. Three languages, i.e. Arabic, Malay, and Thai, for both native male and female speakers were recorded at IIUM Recording Studio. Several experiments have been conducted to find the optimum parameters, i.e. sampling frequency (8000 Hz), LPC order (18), number of hidden layers (300), and learning rate (0.01). Results show that our proposed system is able to recognize the trained languages with the recognition rate of 73.8%. Further research could be conducted to improve the performance using different features, classifiers, or using deep learning neural network. Faculty of Electronic and Computer Engineering, Universiti Teknikal Malaysia Melaka. 2017 Article PeerReviewed application/pdf en http://irep.iium.edu.my/61180/1/GunawanLanguageIdentification_JTEC_3060-8256-1-SM_Dec2017.pdf application/pdf en http://irep.iium.edu.my/61180/7/61180_Development%20of%20language%20identification%20using%20line_SCOPUS.pdf Gunawan, Teddy Surya and Kartiwi, Mira and Ardzemi, Nor Hazima (2017) Development of language identification using line spectral frequencies and learning vector quantization networks. Journal of Telecommunication, Electronic and Computer Engineering, 9 (3-7). pp. 21-27. ISSN 2180-1843 E-ISSN 2289-8131 http://journal.utem.edu.my/index.php/jtec/ |
| repository_type |
Digital Repository |
| institution_category |
Local University |
| institution |
International Islamic University Malaysia |
| building |
IIUM Repository |
| collection |
Online Access |
| language |
English English |
| topic |
TK Electrical engineering. Electronics Nuclear engineering |
| spellingShingle |
TK Electrical engineering. Electronics Nuclear engineering Gunawan, Teddy Surya Kartiwi, Mira Ardzemi, Nor Hazima Development of language identification using line spectral frequencies and learning vector quantization networks |
| description |
Language identification system has become a very active research nowadays due to the need of intercultural human communication. This paper proposed a Language Identification System using Line Spectral Frequencies (LSF) and Linear Vector Quantization (LVQ) network. LSF was used due to its robustness compared to normal linear predictor coefficients (LPC), while LVQ was used due to its low complexity. Three languages, i.e. Arabic, Malay, and Thai, for both native male and female speakers were recorded at IIUM Recording Studio. Several experiments have been conducted to find the optimum parameters, i.e. sampling frequency (8000 Hz), LPC order (18), number of hidden layers (300), and learning rate (0.01). Results show that our proposed system is able to recognize the trained languages with the recognition rate of 73.8%. Further research could be conducted to improve the performance using different features, classifiers, or using deep learning neural network. |
| format |
Article |
| author |
Gunawan, Teddy Surya Kartiwi, Mira Ardzemi, Nor Hazima |
| author_facet |
Gunawan, Teddy Surya Kartiwi, Mira Ardzemi, Nor Hazima |
| author_sort |
Gunawan, Teddy Surya |
| title |
Development of language identification using line spectral frequencies and learning vector quantization networks |
| title_short |
Development of language identification using line spectral frequencies and learning vector quantization networks |
| title_full |
Development of language identification using line spectral frequencies and learning vector quantization networks |
| title_fullStr |
Development of language identification using line spectral frequencies and learning vector quantization networks |
| title_full_unstemmed |
Development of language identification using line spectral frequencies and learning vector quantization networks |
| title_sort |
development of language identification using line spectral frequencies and learning vector quantization networks |
| publisher |
Faculty of Electronic and Computer Engineering, Universiti Teknikal Malaysia Melaka. |
| publishDate |
2017 |
| url |
http://irep.iium.edu.my/61180/ http://irep.iium.edu.my/61180/ http://irep.iium.edu.my/61180/1/GunawanLanguageIdentification_JTEC_3060-8256-1-SM_Dec2017.pdf http://irep.iium.edu.my/61180/7/61180_Development%20of%20language%20identification%20using%20line_SCOPUS.pdf |
| first_indexed |
2023-09-18T21:26:46Z |
| last_indexed |
2023-09-18T21:26:46Z |
| _version_ |
1777412243239993344 |