National and Kapodistrian University of Athens
Ανάπτυξη και υλοποίηση τεχνικών επεξεργασίας σημάτων για τη μελέτη μουσικολογικών μορφωμάτων
Abstract
dc:descriptionThis thesis deals with the recognitional classification of musical patterns. In the context of Greek Traditional music to a predefined set of classes of musical patterns. Two different methodologies have been developed the former employs an extension of the dynamic time warping methodology and the latter is based on discrete observation Hidden Markov models. The feature extraction stage employs in both cases fundamental frequency tracking algorithm. The methods were applied on a testbed consisting of musical patterns stemming from the Greek Traditional clarinet. This thesis lies in the area of pattern recognition and signal processing.
Degree
thesis:*- Grantor dc:publisher
- National and Kapodistrian University of Athens
- Year dc:date
- 2002
Author and committee
dc:creator, dc:contributor.*- Authors dc:creator
-
- Pikrakis, Aggelos
- Πικράκης, Άγγελος
Subjects
dc:subject × 20- Μουσική, Αναγνώριση μορφωμάτων
- Μουσικά μορφώματα, Ταξινόμηση
- Μουσική
- Ψηφιακή επεξεργασία σημάτων
- Hidden Markov μοντέλα
- Δυναμικός προγραμματισμός
- Αλγόριθμοι εύρεσης θεμελιώδους συχνότητας
- Δυναμικός προγραμματισμός με συμφραζόμενα
- Hidden Markov models
- Recognition of musical patterns
- Classification of musical patterns
- Music
- Digital signal processing
- Dynamic programming
- Fundamental frequency tracking
- Context dependent dynamic time warping
- Φυσικές Επιστήμες
- Επιστήμη Ηλεκτρονικών Υπολογιστών και Πληροφορική
- Natural Sciences
- Computer and Information Sciences
Rights
- Language dc:language
- gre
Identifiers
dc:identifier.*- Identifier
- 10.12681/eadd/22217