On the comparison of line spectral frequencies and mel-frequency cepstral coefficients using feedforward neural network for language identification
Of the many audio features available, this paper focuses on the comparison of two most popular features, i.e. line spectral frequencies (LSF) and Mel-Frequency Cepstral Coefficients. We trained a feedforward neural network with various hidden layers and number of hidden nodes to identify five differ...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English English |
| Published: |
Indonesian Journal of Electrical Engineering and Computer Science ( IAES)
2018
|
| Subjects: | |
| Online Access: | http://irep.iium.edu.my/61795/ http://irep.iium.edu.my/61795/1/10880-15119-1-PBGunawanLanguage.pdf http://irep.iium.edu.my/61795/7/61795_On%20the%20Comparison%20of%20Line%20Spectral%20Frequencies%20_scopus.pdf |
| _version_ | 1848785735402913792 |
|---|---|
| author | Gunawan, Teddy Surya Kartiwi, Mira |
| author_facet | Gunawan, Teddy Surya Kartiwi, Mira |
| author_sort | Gunawan, Teddy Surya |
| building | IIUM Repository |
| collection | Online Access |
| description | Of the many audio features available, this paper focuses on the comparison of two most popular features, i.e. line spectral frequencies (LSF) and Mel-Frequency Cepstral Coefficients. We trained a feedforward neural network with various hidden layers and number of hidden nodes to identify five different languages, i.e. Arabic, Chinese, English, Korean, and Malay. LSF, MFCC, and combination of both features were extracted as the feature vectors. Systematic experiments have been conducted to find the optimum parameters, i.e. sampling frequency, frame size, model order, and structure of neural network. The recognition rate per frame was converted to recognition rate per audio file using majority voting. On average, the recognition rate for LSF, MFCC, and combination of both features are 96%, 92%, and 96%, respectively. Therefore, LSF is the most suitable features to be utilized for language identification using feedforward neural network classifier. |
| first_indexed | 2025-11-14T16:57:52Z |
| format | Article |
| id | iium-61795 |
| institution | International Islamic University Malaysia |
| institution_category | Local University |
| language | English English |
| last_indexed | 2025-11-14T16:57:52Z |
| publishDate | 2018 |
| publisher | Indonesian Journal of Electrical Engineering and Computer Science ( IAES) |
| recordtype | eprints |
| repository_type | Digital Repository |
| spelling | iium-617952018-02-13T03:05:26Z http://irep.iium.edu.my/61795/ On the comparison of line spectral frequencies and mel-frequency cepstral coefficients using feedforward neural network for language identification Gunawan, Teddy Surya Kartiwi, Mira TK7885 Computer engineering Of the many audio features available, this paper focuses on the comparison of two most popular features, i.e. line spectral frequencies (LSF) and Mel-Frequency Cepstral Coefficients. We trained a feedforward neural network with various hidden layers and number of hidden nodes to identify five different languages, i.e. Arabic, Chinese, English, Korean, and Malay. LSF, MFCC, and combination of both features were extracted as the feature vectors. Systematic experiments have been conducted to find the optimum parameters, i.e. sampling frequency, frame size, model order, and structure of neural network. The recognition rate per frame was converted to recognition rate per audio file using majority voting. On average, the recognition rate for LSF, MFCC, and combination of both features are 96%, 92%, and 96%, respectively. Therefore, LSF is the most suitable features to be utilized for language identification using feedforward neural network classifier. Indonesian Journal of Electrical Engineering and Computer Science ( IAES) 2018-04 Article PeerReviewed application/pdf en http://irep.iium.edu.my/61795/1/10880-15119-1-PBGunawanLanguage.pdf application/pdf en http://irep.iium.edu.my/61795/7/61795_On%20the%20Comparison%20of%20Line%20Spectral%20Frequencies%20_scopus.pdf Gunawan, Teddy Surya and Kartiwi, Mira (2018) On the comparison of line spectral frequencies and mel-frequency cepstral coefficients using feedforward neural network for language identification. Indonesian Journal of Electrical Engineering and Computer Science, 10 (1). pp. 168-175. ISSN 2502-4752 E-ISSN 2502-4760 http://iaescore.com/journals/index.php/IJEECS/ 10.11591/ijeecs.v10.i1.pp168-175 |
| spellingShingle | TK7885 Computer engineering Gunawan, Teddy Surya Kartiwi, Mira On the comparison of line spectral frequencies and mel-frequency cepstral coefficients using feedforward neural network for language identification |
| title | On the comparison of line spectral frequencies and mel-frequency cepstral coefficients using feedforward neural network for language identification |
| title_full | On the comparison of line spectral frequencies and mel-frequency cepstral coefficients using feedforward neural network for language identification |
| title_fullStr | On the comparison of line spectral frequencies and mel-frequency cepstral coefficients using feedforward neural network for language identification |
| title_full_unstemmed | On the comparison of line spectral frequencies and mel-frequency cepstral coefficients using feedforward neural network for language identification |
| title_short | On the comparison of line spectral frequencies and mel-frequency cepstral coefficients using feedforward neural network for language identification |
| title_sort | on the comparison of line spectral frequencies and mel-frequency cepstral coefficients using feedforward neural network for language identification |
| topic | TK7885 Computer engineering |
| url | http://irep.iium.edu.my/61795/ http://irep.iium.edu.my/61795/ http://irep.iium.edu.my/61795/ http://irep.iium.edu.my/61795/1/10880-15119-1-PBGunawanLanguage.pdf http://irep.iium.edu.my/61795/7/61795_On%20the%20Comparison%20of%20Line%20Spectral%20Frequencies%20_scopus.pdf |