Musical Data Mining by Temporal Patterns

• Grant number: 12/17961-0
• Support Opportunities: Scholarships in Brazil - Post-Doctoral
• Start date: March 01, 2013
• End date: February 29, 2016
• Field of knowledge: Physical Sciences and Mathematics - Computer Science - Computing Methodologies and Techniques
• Principal Investigator: Francisco Aparecido Rodrigues
• Grantee: Débora Cristina Corrêa
• Host Institution: Instituto de Ciências Matemáticas e de Computação (ICMC). Universidade de São Paulo (USP). São Carlos , SP, Brazil

Abstract

The constant growth of online music dataset and applications has required advances in Music Information Retrieval (MIR) research. Music genres and annotated mood have received much attention in the last decades as descriptors of content-based systems, since they summarize common characteristics of music and are included in the set of principal tools for content-based music retrieval and organization. However, their inherent relationship is rarely explored in the literature. Within this context, the project aims at contributing to the existing investigation of how music genres can be related with mood and thus establish complementary descriptors that can be used to improve current applications of music information retrieval systems. To do so, we investigate whether or not the presence of temporal patterns in thestructure of music can be used for establishing a quantitativerelationship between genres and subjective aspects such as the mood, dynamism and emotion. Our approach considers complex networks to model the data and the relationship between elements. Complex networks have shown to be promising mechanisms to represent several aspects of nature, since their topological and structural features help in the understanding the relationship, properties and intrinsic characteristics of the data. The methodology is directlyapplied to applications like similarity search, music composition,recommendations systems and hits prediction.

Scientific publications

(References retrieved automatically from Web of Science and SciELO through information on FAPESP grants and their corresponding numbers as mentioned in the publications by the authors)

FERREIRA, MARTHA DAIS; CORREA, DEBORA CRISTINA; NONATO, LUIS GUSTAVO; DE MELLO, RODRIGO FERNANDES. Designing architectures of convolutional neural networks to solve practical problems. EXPERT SYSTEMS WITH APPLICATIONS, v. 94, p. 205-217, MAR 15 2018. (11/22749-8, 14/13323-5, 12/17961-0)

FERREIRA, MARTHA DAIS; CORREA, DEBORA CRISTINA; GRIVET, MARCOS ANTONIO; DOS SANTOS, GEOVAN TAVARES; DE MELLO, RODRIGO FERNANDES; NONATO, LUIS GUSTAVO. On Accuracy and Time Processing Evaluation of Cover Song Identification Systems. JOURNAL OF NEW MUSIC RESEARCH, v. 45, n. 4, p. 333-342, DEC 2016. (11/22749-8, 14/13323-5, 12/17961-0)

CORREA, DEBORA C.; AP RODRIGUES, FRANCISCO. A survey on symbolic data-based music genre classification. EXPERT SYSTEMS WITH APPLICATIONS, v. 60, p. 190-210, OCT 30 2016. (11/50761-2, 13/26416-9, 12/17961-0)