Segmentation process and spectral characteristics in the determination of musical genres

Over the past few years there has been a tendency to store audio tracks for later use on CD-DVDs, HDD-SSDs as well as on the internet, which makes it challenging to classify the information either online or offline. For this purpose, the audio tracks must be tagged. Tags are said to be texts based on the semantic information of the sound [1]. Thus, music analysis can be done in several ways [2] since music is identified by its genre, artist, instruments and structure, by a tagging system that can be manual or automatic. The manual tagging allows the visualization of the behavior of an audio track either in time domain or in frequency domain as in the spectrogram, making it possible to classify the songs without listening to them. However, this process is very time consuming and labor intensive, including health problems [3] which shows that "the volume, sound sensitivity, time and cost required for a manual labeling process is generally prohibitive. Three fundamental steps are required to carry out automatic labelling: pre-processing, feature extraction and classification [4]. The present study developed an algorithm for performing automatic classification of music genres using a segmentation process employing spectral characteristics such as centroid (SC), flatness (SF) and spread (SS), as well as a time spectral characteristic.

• Autores: amelec, viloria; Pineda Lezama, Omar Bonerge; Cabrera, Danelys
• Tipo de recurso: Article of journal
• Fecha de publicación: 2020
• Institución: Corporación Universidad de la Costa
• Repositorio: REDICUC - Repositorio CUC
• Idioma: eng
• OAI Identifier: oai:repositorio.cuc.edu.co:11323/7657
• Acceso en línea: https://hdl.handle.net/11323/7657; https://repositorio.cuc.edu.co/
• Palabra clave: Supervised learning algorithms; Music genres classification; Centroid (SC); Flatness (SF); Spread (SS)
• Rights: openAccess
• License: CC0 1.0 Universal