Automatic musical instrument recognition and related topics

L' identification Automatique d'Instruments de Musique (IAIM) est composée de plusieurs étapes qui constituent chacune un défi pour les chercheurs. Les différentes étapes, présentées dans cette thèse, sont les suivantes: obtenir et formater les bases de données de sons pour l'apprentissage et l'évaluation, calculer les descripteurs des sons, procéder au nettoyage automatique des bases de données, attribuer des poids aux descripteurs et réduire leur dimension, et, enfin, classer les sons selon leur appartenance aux différents instruments. Mener une évaluation correcte du déroulement de l IAIM constitue aussi un travail fondamental. Ce travail traite en détail des différentes étapes du processus de l'IAIM et, tout en comblant des lacunes et des défaillances dans l'état de l'art, introduit de nouvelles techniques et de nouvelles méthodes pour le perfectionner: il permet d'identifier les instruments de musique à partir des tons séparés, des solos, de la musique polyphonique et multi-instrumentale .The thesis deals with various aspects of Automatic Musical Instrument Recognition (AMIR). AMIR means, intuitively speaking, that given a musical recording, the computer attempts to identify which parts of the music are performed by which musical instruments. AMIR research has gained popularity over the last 10 years especially due to its applicability as a component inside Intelligent music search-engines, which can allow searching the Internet or mass-storage devices in personal MP3 players for music using intelligent criteria such as musical style or composition - as opposed to searches involving only textual information provided with the musical files. Other usages of AMIR include integration and improvement of other Musical Information Retrieval tasks such as Automatic Transcription and Score Alignment, and as a tool in applications for composers and recording studios. AMIR is a compound process involving many challenging stages. The various stages of the AMIR process as presented in this thesis include obtaining and formatting of Learning and Test sound databases, computing feature descriptors on the sounds, automatic purging of the databases, feature weighting and dimension reduction of the feature descriptor space and finally, classification of the sounds as belonging to different instruments. Performing informative evaluation of the AMIR process is also important and non-trivial. This work deals in detail with the different stages of the AMIR process and while filling holes in the theory it introduces new techniques and methods for performing many of the tasks, accomplishing AMIR of separate tones, Solo performances and polyphonic, multi-instrumental music.PARIS-BIUSJ-Thèses (751052125) / SudocPARIS-BIUSJ-Physique recherche (751052113) / SudocSudocFranceF