The computational detection of musical patterns is widely studied in the field of Music Information Retrieval and has numerous applications. However, pattern detection in real-time has not yet received adequate attention. The real-time detection is important in several application domains, especially in the field of the Internet of Musical Things. This study considers a single musical instrument and investigates the detection in real-time of patterns of a monophonic music stream. We present a representation mechanism to denote musical notes as a single column matrix, whose content corresponds to three key attributes of each musical note-pitch, amplitude and duration. The note attributes are obtained from a symbolic MIDI representation. Based on such representation, we compare the most prominent candidate methods based on neural networks and one deterministic method. Numerical results show the accuracy of each method, and allow us to characterize the trade-offs among those methods.

The computational detection of musical patterns is widely studied in the field of Music Information Retrieval and has numerous applications. However, pattern detection in real-time has not yet received adequate attention. The real-time detection is important in several application domains, especially in the field of the Internet of Musical Things. This study considers a single musical instrument and investigates the detection in real-time of patterns of a monophonic music stream. We present a representation mechanism to denote musical notes as a single column matrix, whose content corresponds to three key attributes of each musical note-pitch, amplitude and duration. The note attributes are obtained from a symbolic MIDI representation. Based on such representation, we compare the most prominent candidate methods based on neural networks and one deterministic method. Numerical results show the accuracy of each method, and allow us to characterize the trade-offs among those methods.

Towards Real-Time Detection of Symbolic Musical Patterns: Probabilistic vs. Deterministic Methods / Silva, N.; Fischione, C.; Turchet, L.. - 2020-:(2020), pp. 238-246. (Intervento presentato al convegno 27th Conference of Open Innovations Association FRUCT, FRUCT 2020 tenutosi a ita nel 2020) [10.23919/FRUCT49677.2020.9211010].

Towards Real-Time Detection of Symbolic Musical Patterns: Probabilistic vs. Deterministic Methods

Turchet L.
2020-01-01

Abstract

The computational detection of musical patterns is widely studied in the field of Music Information Retrieval and has numerous applications. However, pattern detection in real-time has not yet received adequate attention. The real-time detection is important in several application domains, especially in the field of the Internet of Musical Things. This study considers a single musical instrument and investigates the detection in real-time of patterns of a monophonic music stream. We present a representation mechanism to denote musical notes as a single column matrix, whose content corresponds to three key attributes of each musical note-pitch, amplitude and duration. The note attributes are obtained from a symbolic MIDI representation. Based on such representation, we compare the most prominent candidate methods based on neural networks and one deterministic method. Numerical results show the accuracy of each method, and allow us to characterize the trade-offs among those methods.
2020
IEEE Conference of Open Innovation Association, FRUCT
New York
IEEE Computer Society
978-952-69244-3-4
Silva, N.; Fischione, C.; Turchet, L.
Towards Real-Time Detection of Symbolic Musical Patterns: Probabilistic vs. Deterministic Methods / Silva, N.; Fischione, C.; Turchet, L.. - 2020-:(2020), pp. 238-246. (Intervento presentato al convegno 27th Conference of Open Innovations Association FRUCT, FRUCT 2020 tenutosi a ita nel 2020) [10.23919/FRUCT49677.2020.9211010].
File in questo prodotto:
Non ci sono file associati a questo prodotto.

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11572/287082
 Attenzione

Attenzione! I dati visualizzati non sono stati sottoposti a validazione da parte dell'ateneo

Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 2
  • ???jsp.display-item.citation.isi??? 0
social impact