Sunday 24th of September 2017
 

Fast Algorithm for In situ transcription of musical signals : Case of lute music


Lhoussine Bahatti, Omar Bouattane, Mimoun Zazoui and Ahmed Rebbani

In this paper, we propose a fast and accurate transcription method of a musical signal. It consists of extracting the musical information from the temporal evolution of the generated signal by the instrument. Each note (primary) will mainly be represented by a finite set of basic attributes (pitch, partial, energy, duration,). To do so, we begin by extracting each note by selecting the beginning of its appearance (onset detection), then proceeding by segmenting the signal, in order to delimit each note, which is to be identified later by determining its remaining features. The proposed method is an extension of the well known spectral based method. It is specially designed for oriental music which is characterized by its richness in tone that can be extended to tone. It aims to detect and isolate notes from a real audio signal recorded from an Oriental lute in an ordinary environment, then exploits the constraints of the lutes sound to improve the performance of the proposed transcriber. This method also includes, preprocessing and post processing based mainly on the surrounding noise, and echo. Subsequently, we present an interpretation of the results and rigorous assessment of the method through modeling the lute string motion.

Keywords: : musical note, oriental music; onset, pitch, lute, tone, RAST, string motion

Download Full-Text


ABOUT THE AUTHORS

Lhoussine Bahatti
Lhoussine BAHATTI was born in 1968 in MIDELT, Morocco. He is now a teacher of control, automatic regulation and signal processing, and researcher at the University Hassan II Mohammedia, ENSET Institute. His research is focused on Music information retrieval. He Received the B.S. degree in Electronics in 1987 and the Aggregation Electrical Engineering degree in 1995 from the ENS CACHAN France. He received the DEA diploma in information processing in 1997 from the Ben Mísik University of Casablanca MOROCCO

Omar Bouattane
Omar BOUATTANE was born in 1962 in FIGUIG, south of Morocco. He has his Ph.D. degree in 2001 in Parallel Image Processing on Reconfigurable Computing Mesh from the Faculty of Science Ain Chock, CASABLANCA. He has published more than 30 research publications and brevets in various National, International conference proceedings and Journals. His research interests include Massively Parallel Architectures, cluster analysis, pattern recognition, image processing and fuzzy logic.

Mimoun Zazoui
Mimoun ZAZOUI is a professor at the Faculty of Science and Technology of Mohammedia (FSTM). Chair of the Moroccan Society of Renewable Energy. He has coordinated various research projects and training at national and international level and within the framework of cooperation. He has also gained considerable experience in the area of academic capacity; he is Vice Dean and Director of Graduate Studies at the FSTM. He is also responsible for unit training and research in Thin Film Materials and Systems for Energy Conversion. He is also Director of the Laboratory of Physics of Condensed Matter at the FSTM.

Ahmed Rebbani
Ahmed REBBANI was born in 1967, in TAZA, Morocco. He is now a teacher of computer networks, and researcher at the University Hassan II Mohammedia, ENSET Institute. His research is focused Source separation. He Received the B.S. degree in Electronics in 1988 the M.S. degree in Applied Electronics in 1992 from the ENSET Institute, Mohammedia, Morocco. He received the DEA diploma in information processing in 1997 from the Ben Mísik University of Casablanca MOROCCO


IJCSI Published Papers Indexed By:

 

 

 

 
About IJCSI

IJCSI is a refereed open access international journal for scientific papers dealing in all areas of computer science research...

Learn more »
Join Us
FAQs

Read the most frequently asked questions about IJCSI.

Frequently Asked Questions (FAQs) »
Get in touch

Phone: +230 911 5482
Email: info@ijcsi.org

More contact details »