Automatic Classification of Musical Instrument Samples
Uloženo v:
| Název: | Automatic Classification of Musical Instrument Samples |
|---|---|
| Autoři: | Daniele Scarano |
| Informace o vydavateli: | Zenodo |
| Rok vydání: | 2016 |
| Sbírka: | Zenodo |
| Témata: | machine learning, signal processing, Freesound, content based classification |
| Popis: | Automatic classification of musical instrument is an old research topic in music information retrieval. In this work we address the problem of the classification using musical instrument single note samples from Freesound and we put the accent on the content analysis of the sound and how those content information are connected to the physical characteristics of each instrument. We build a taxonomy based on instrument families and mode of excitation. The musical instruments play a central role in this work and the studies on timbre are used as a methodological base to apply feature selection to our complete set of descriptors, the aim of this is to find which descriptors are relevant to describe a specific instrument. The machine learning then is used as an instrument to evaluate our choices, to identify weakness and problem in the current implementation of audio descriptors. |
| Druh dokumentu: | text |
| Jazyk: | English |
| Relation: | https://zenodo.org/communities/smc-master/; https://zenodo.org/records/3786212; oai:zenodo.org:3786212; https://doi.org/10.5281/zenodo.3786212 |
| DOI: | 10.5281/zenodo.3786212 |
| Dostupnost: | https://doi.org/10.5281/zenodo.3786212 https://zenodo.org/records/3786212 |
| Rights: | Creative Commons Attribution 4.0 International ; cc-by-4.0 ; https://creativecommons.org/licenses/by/4.0/legalcode |
| Přístupové číslo: | edsbas.BDD3BA2E |
| Databáze: | BASE |
Nájsť tento článok vo Web of Science | Abstrakt: | Automatic classification of musical instrument is an old research topic in music information retrieval. In this work we address the problem of the classification using musical instrument single note samples from Freesound and we put the accent on the content analysis of the sound and how those content information are connected to the physical characteristics of each instrument. We build a taxonomy based on instrument families and mode of excitation. The musical instruments play a central role in this work and the studies on timbre are used as a methodological base to apply feature selection to our complete set of descriptors, the aim of this is to find which descriptors are relevant to describe a specific instrument. The machine learning then is used as an instrument to evaluate our choices, to identify weakness and problem in the current implementation of audio descriptors. |
|---|---|
| DOI: | 10.5281/zenodo.3786212 |