Loading...

Automatic Recognition of Quranic Maqams Using Machine Learning

Khodabandeh, Mohammad Javad | 2021

634 Viewed
  1. Type of Document: M.Sc. Thesis
  2. Language: Farsi
  3. Document No: 54400 (31)
  4. University: Sharif University of Technology
  5. Department: Languages and Linguistics Center
  6. Advisor(s): Sameti, Hossein; Bahrani, Mohammad
  7. Abstract:
  8. Automatic recognition of musical Maqams has been one of the challenging problems in Music Information Retrieval. Despite the increasing amount of related research in recent years, we are still far away from building related real-life applications. Nevertheless, a very small portion of these research is dedicated to automatic recognition of Maqams in recitation of the Holy Quran. In this thesis, as a first attempt, we have used machine learning methods to classify six Maqam families which are commonly used in Quran recitation. Also, due to the lack of pre-exisiting datasets, we have annotated approximately 1325 minutes of Tadwir recitation from two prominent Egyptian reciters, i.e., Muhammad Siddiq Al-Minshawi, and Shahat Muhammad Anwar. Three different classifiers have been used: Support Vector Machines, Feed-forward Neural Network, and Long Short-term Memory Recurrent Neural Network. To represent audio samples, two commonly recognized features were extracted and compared: Mel-frequency Cepstral Coefficients, and Harmonic Pitch Class Profiles. The results demonstrate significant superiority of Harmonic Pitch Class Profiles and Long Short-term Memory Recurrent Neural Network in representation of Maqams and their classification, respectively, over the other methods. As such, F-scores of the three mentioned classifiers are 72.71, 75.11, and 81.48 percent, respectively, for Minshawi's recitation, and 51.73, 61.22, and 69.75 percent, respectively, for Shahat's recitation. Results of two-, three-, four-, and five-class cases are also reported in Support Vector Machine classifier, in addition to the six-class case.

  9. Keywords:
  10. Music Information Retrieval ; Machine Learning ; Automatic Quranic Maqams Recognition ; Feedforward Neural Network

 Digital Object List

 Bookmark

...see more