The paper aims to propose song recognition on an IoT device that continuously monitors FM Radio stations connected to cloud processing and storage. Radio stations and music companies have advanced in music markets, in particular by creating ways to analyze the broadcast song and listening habits through modern services and platforms. In this research, we focused on merging two main areas which are utilizing IoT devices as an FM audio receiver and further providing a suitable song recognition architecture. We evaluated the performance of the proposed IoT Based song recognition framework with an entire collection of a thousand song database. Also, we optimize the performance and evaluated with state of the art Landmark-based and Cache MEM in term of speed and accuracy. To produce a scalable design, we also provide an in-depth discussion on the K-means database clustering algorithm whereby the main objective was to reduce the search space within the database.

IoT based song recognition for fm radio station broadcasting

Sahbudin
Membro del Collaboration Group
;
Chaouch C.
Membro del Collaboration Group
;
Scarpa M.
Membro del Collaboration Group
;
Serrano S.
Membro del Collaboration Group
2019-01-01

Abstract

The paper aims to propose song recognition on an IoT device that continuously monitors FM Radio stations connected to cloud processing and storage. Radio stations and music companies have advanced in music markets, in particular by creating ways to analyze the broadcast song and listening habits through modern services and platforms. In this research, we focused on merging two main areas which are utilizing IoT devices as an FM audio receiver and further providing a suitable song recognition architecture. We evaluated the performance of the proposed IoT Based song recognition framework with an entire collection of a thousand song database. Also, we optimize the performance and evaluated with state of the art Landmark-based and Cache MEM in term of speed and accuracy. To produce a scalable design, we also provide an in-depth discussion on the K-means database clustering algorithm whereby the main objective was to reduce the search space within the database.
2019
978-1-5386-8052-0
File in questo prodotto:
Non ci sono file associati a questo prodotto.
Pubblicazioni consigliate

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/11570/3150651
 Attenzione

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

Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 6
  • ???jsp.display-item.citation.isi??? 1
social impact