Berauti Spectral Subtraction dengan Gaussian Window untuk Peningkatan Akurasi Pengenalan Ucapan Berderau
The accuracy of speech recognition system decreases when used on a noisy speech. Therefore, the speech recognition system needs to be supported by a speech enhancement method. This study proposes Berauti spectral subtraction method that uses gaussian window and minimum statistics noise estimation in...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Universitas Andalas
2018-11-01
|
| Series: | Jurnal Nasional Teknik Elektro |
| Subjects: | |
| Online Access: | http://jnte.ft.unand.ac.id/index.php/jnte/article/view/497/361 |
| _version_ | 1818577283331391488 |
|---|---|
| author | Fitrilina Fitrilina Winda Alfin Fajar Afriyansah |
| author_facet | Fitrilina Fitrilina Winda Alfin Fajar Afriyansah |
| author_sort | Fitrilina Fitrilina |
| collection | DOAJ |
| description | The accuracy of speech recognition system decreases when used on a noisy speech. Therefore, the speech recognition system needs to be supported by a speech enhancement method. This study proposes Berauti spectral subtraction method that uses gaussian window and minimum statistics noise estimation in order to improve the quality of noisy speech hence increase the accuracy of noisy speech recognition. Speech recognition system is built using the Hidden Markov Model Toolkit (HTK). This study applied three types of noise, five SNR levels, six oversubtraction values and four sidelobe gaussian window attenuation values with 1500 speech signals. Improvement of speech recognition accuracy using Gaussian window is compared with Hamming window. The results of the study shows that sidelobe and oversubtraction attenuation values affects recognition accuracy. The average speech recognition accuracy using gaussian window improve about 36.4% which is obtained at oversubtraction 4.75 and sidelobe attenuation = 1.5. Whereas, application of hamming window improves the accuracy about 18,7 % which is obtained at oversubtraction 2.5. Spectral subtraction using gaussian window or hamming window is able to improve the speech recognition accuracy, but gaussian window is better than hamming window. |
| first_indexed | 2024-12-16T06:27:27Z |
| format | Article |
| id | doaj.art-80f0fb8143cd4ed2b310b584d78d5f27 |
| institution | Directory Open Access Journal |
| issn | 2302-2949 2407-7267 |
| language | English |
| last_indexed | 2024-12-16T06:27:27Z |
| publishDate | 2018-11-01 |
| publisher | Universitas Andalas |
| record_format | Article |
| series | Jurnal Nasional Teknik Elektro |
| spelling | doaj.art-80f0fb8143cd4ed2b310b584d78d5f272022-12-21T22:40:59ZengUniversitas AndalasJurnal Nasional Teknik Elektro2302-29492407-72672018-11-0173175182Berauti Spectral Subtraction dengan Gaussian Window untuk Peningkatan Akurasi Pengenalan Ucapan BerderauFitrilina Fitrilina0Winda Alfin1Fajar Afriyansah2Universitas Andalas Universitas Andalas Universitas Andalas The accuracy of speech recognition system decreases when used on a noisy speech. Therefore, the speech recognition system needs to be supported by a speech enhancement method. This study proposes Berauti spectral subtraction method that uses gaussian window and minimum statistics noise estimation in order to improve the quality of noisy speech hence increase the accuracy of noisy speech recognition. Speech recognition system is built using the Hidden Markov Model Toolkit (HTK). This study applied three types of noise, five SNR levels, six oversubtraction values and four sidelobe gaussian window attenuation values with 1500 speech signals. Improvement of speech recognition accuracy using Gaussian window is compared with Hamming window. The results of the study shows that sidelobe and oversubtraction attenuation values affects recognition accuracy. The average speech recognition accuracy using gaussian window improve about 36.4% which is obtained at oversubtraction 4.75 and sidelobe attenuation = 1.5. Whereas, application of hamming window improves the accuracy about 18,7 % which is obtained at oversubtraction 2.5. Spectral subtraction using gaussian window or hamming window is able to improve the speech recognition accuracy, but gaussian window is better than hamming window.http://jnte.ft.unand.ac.id/index.php/jnte/article/view/497/361Berauti spectral subtractiongaussian windowpengenalan ucapan |
| spellingShingle | Fitrilina Fitrilina Winda Alfin Fajar Afriyansah Berauti Spectral Subtraction dengan Gaussian Window untuk Peningkatan Akurasi Pengenalan Ucapan Berderau Jurnal Nasional Teknik Elektro Berauti spectral subtraction gaussian window pengenalan ucapan |
| title | Berauti Spectral Subtraction dengan Gaussian Window untuk Peningkatan Akurasi Pengenalan Ucapan Berderau |
| title_full | Berauti Spectral Subtraction dengan Gaussian Window untuk Peningkatan Akurasi Pengenalan Ucapan Berderau |
| title_fullStr | Berauti Spectral Subtraction dengan Gaussian Window untuk Peningkatan Akurasi Pengenalan Ucapan Berderau |
| title_full_unstemmed | Berauti Spectral Subtraction dengan Gaussian Window untuk Peningkatan Akurasi Pengenalan Ucapan Berderau |
| title_short | Berauti Spectral Subtraction dengan Gaussian Window untuk Peningkatan Akurasi Pengenalan Ucapan Berderau |
| title_sort | berauti spectral subtraction dengan gaussian window untuk peningkatan akurasi pengenalan ucapan berderau |
| topic | Berauti spectral subtraction gaussian window pengenalan ucapan |
| url | http://jnte.ft.unand.ac.id/index.php/jnte/article/view/497/361 |
| work_keys_str_mv | AT fitrilinafitrilina berautispectralsubtractiondengangaussianwindowuntukpeningkatanakurasipengenalanucapanberderau AT windaalfin berautispectralsubtractiondengangaussianwindowuntukpeningkatanakurasipengenalanucapanberderau AT fajarafriyansah berautispectralsubtractiondengangaussianwindowuntukpeningkatanakurasipengenalanucapanberderau |