Automated tabla syllable transcription using image processing techniques
- PDF / 1,114,915 Bytes
- 15 Pages / 439.642 x 666.49 pts Page_size
- 91 Downloads / 203 Views
Automated tabla syllable transcription using image processing techniques Raghavendra Bhalarao1
· Mitesh Raval1
Received: 26 August 2019 / Revised: 7 July 2020 / Accepted: 21 July 2020 / © Springer Science+Business Media, LLC, part of Springer Nature 2020
Abstract In this paper, we have proposed an automated tabla syllable transcription method using image processing technique. As for a beginner tabla learner, the learning is faster by visualizing things rather than just listening. Therefore, we have adopted this technique for our study. We have used a human perception based approach for learning tabla and implemented the same. We have created three regions of interest for each drum, dayan and bayan. The placement of the fingers’ image feature over this region is tracked to determine the exact region where it strikes and produces a particular syllable. Each frame is initially labeled to a syllable. Finally, we have used supervised classification to prune the labeling for each stroke based on its image for a particular syllable by comparing incoming frames to the reference image using the structural similarity index. Based on this the syllables are classified and automatic transcription is done. Using the proposed method, we are proficiently able to transcript 97.14% of the tabla syllables with F1 score of 0.98. Keywords Automatic transcription · Tabla · Image processing · SURF features · SSIM
1 Introduction A musician often plays music by reading from a written-out music sheet. They convert the notes written on a page into a musical piece. Transcribing music is reverse of this process [29]. A written representation of the music is essential for the transcription from a recording. Musicians often use the transcription of music to understand it better. A transcribed piece of music can become a powerful resource for a music learner. Since the transcribing process can be sluggish and erroneous, it requires a certain level of musical expertise. Unfortunately, it becomes a tedious job. Thus, the theory of automatic music transcription (AMT) comes into existence. AMT converts the recorded music into a written set of music using an algorithmic approach. It has been an influencing area of research for over 40 years in the field of music signal processing [5, 19]. Raghavendra Bhalarao
[email protected] 1
Department of Electrical Engineering, Institute of Infrastructure, Technology, Research and Management (IITRAM), Ahmedabad, India
Multimedia Tools and Applications
The development of digital music has considerably expanded the accessibility of content over the most recent couple of years. As the name suggests, digital music represents an analog sound in discrete values. For the proper analysis of this data, Music Information Retrieval (MIR) has been an important field of research [10]. A significant issue in MIR is AMT, where the musical audio signal is converted into musical notations such as Musical Instrument Digital Interface (MIDI) file [26]. AMT, in general, is typically a procedure of separati
Data Loading...
