Automatic Recognition of Arabic Poetry Meter from Speech Signal using Long Short-term Memory and Support Vector Machine
The recognition of the poetry meter in spoken lines is a natural language processing application that aims to identify a stressed and unstressed syllabic pattern in a line of a poem. Stateof-the-art studies include few works on the automatic recognition of Arud meters, all of which are text-based mo...
| Main Author: | |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Koya University
2020-04-01
|
| Series: | ARO-The Scientific Journal of Koya University |
| Subjects: | |
| Online Access: | https://aro.koyauniversity.org/index.php/aro/article/view/631 |
| _version_ | 1797724194076622848 |
|---|---|
| author | Abdulbasit K. Al-Talabani |
| author_facet | Abdulbasit K. Al-Talabani |
| author_sort | Abdulbasit K. Al-Talabani |
| collection | DOAJ |
| description | The recognition of the poetry meter in spoken lines is a natural language processing application that aims to identify a stressed and unstressed syllabic pattern in a line of a poem. Stateof-the-art studies include few works on the automatic recognition of Arud meters, all of which are text-based models, and none is voice based. Poetry meter recognition is not easy for an ordinary reader, it is very difficult for the listener and it is usually performed manually by experts. This paper proposes a model to detect the poetry meter from a single spoken line (“Bayt”) of an Arabic poem. Data of 230 samples collected from 10 poems of Arabic poetry, including three meters read by two speakers, are used in this work. The work adopts the extraction of linear prediction cepstrum coefficient and Mel frequency cepstral coefficient (MFCC) features, as a time series input to the proposed long short-term memory (LSTM) classifier, in addition to a global feature set that is computed using some statistics of the features across all of the frames to feed the support vector machine (SVM) classifier. The results show that the SVM model achieves the highest accuracy in the speakerdependent approach. It improves results by 3%, as compared to the state-of-the-art studies, whereas for the speaker-independent approach, the MFCC feature using LSTM exceeds the other proposed models. |
| first_indexed | 2024-03-12T10:13:56Z |
| format | Article |
| id | doaj.art-92bc0e6d61f14c068c5665f002bece74 |
| institution | Directory Open Access Journal |
| issn | 2410-9355 2307-549X |
| language | English |
| last_indexed | 2024-03-12T10:13:56Z |
| publishDate | 2020-04-01 |
| publisher | Koya University |
| record_format | Article |
| series | ARO-The Scientific Journal of Koya University |
| spelling | doaj.art-92bc0e6d61f14c068c5665f002bece742023-09-02T10:42:30ZengKoya UniversityARO-The Scientific Journal of Koya University2410-93552307-549X2020-04-018110.14500/aro.10631Automatic Recognition of Arabic Poetry Meter from Speech Signal using Long Short-term Memory and Support Vector MachineAbdulbasit K. Al-Talabani0Department of Software Engineering, Faculty of Engineering, Koya University, Koya KOY45, Kurdistan RegionThe recognition of the poetry meter in spoken lines is a natural language processing application that aims to identify a stressed and unstressed syllabic pattern in a line of a poem. Stateof-the-art studies include few works on the automatic recognition of Arud meters, all of which are text-based models, and none is voice based. Poetry meter recognition is not easy for an ordinary reader, it is very difficult for the listener and it is usually performed manually by experts. This paper proposes a model to detect the poetry meter from a single spoken line (“Bayt”) of an Arabic poem. Data of 230 samples collected from 10 poems of Arabic poetry, including three meters read by two speakers, are used in this work. The work adopts the extraction of linear prediction cepstrum coefficient and Mel frequency cepstral coefficient (MFCC) features, as a time series input to the proposed long short-term memory (LSTM) classifier, in addition to a global feature set that is computed using some statistics of the features across all of the frames to feed the support vector machine (SVM) classifier. The results show that the SVM model achieves the highest accuracy in the speakerdependent approach. It improves results by 3%, as compared to the state-of-the-art studies, whereas for the speaker-independent approach, the MFCC feature using LSTM exceeds the other proposed models.https://aro.koyauniversity.org/index.php/aro/article/view/631Speech processingLong short-term memorySupport vector machineProsodyCepstral features |
| spellingShingle | Abdulbasit K. Al-Talabani Automatic Recognition of Arabic Poetry Meter from Speech Signal using Long Short-term Memory and Support Vector Machine ARO-The Scientific Journal of Koya University Speech processing Long short-term memory Support vector machine Prosody Cepstral features |
| title | Automatic Recognition of Arabic Poetry Meter from Speech Signal using Long Short-term Memory and Support Vector Machine |
| title_full | Automatic Recognition of Arabic Poetry Meter from Speech Signal using Long Short-term Memory and Support Vector Machine |
| title_fullStr | Automatic Recognition of Arabic Poetry Meter from Speech Signal using Long Short-term Memory and Support Vector Machine |
| title_full_unstemmed | Automatic Recognition of Arabic Poetry Meter from Speech Signal using Long Short-term Memory and Support Vector Machine |
| title_short | Automatic Recognition of Arabic Poetry Meter from Speech Signal using Long Short-term Memory and Support Vector Machine |
| title_sort | automatic recognition of arabic poetry meter from speech signal using long short term memory and support vector machine |
| topic | Speech processing Long short-term memory Support vector machine Prosody Cepstral features |
| url | https://aro.koyauniversity.org/index.php/aro/article/view/631 |
| work_keys_str_mv | AT abdulbasitkaltalabani automaticrecognitionofarabicpoetrymeterfromspeechsignalusinglongshorttermmemoryandsupportvectormachine |