Low-complexity acoustic scene classification for multi-device audio: analysis of DCASE 2021 Challenge systems

Tutkimustuotos: KonferenssiartikkeliScientificvertaisarvioitu

Abstrakti

This paper presents the details of Task 1A Acoustic Scene Classification in the DCASE 2021 Challenge. The task targeted development of low-complexity solutions with good generalization properties. The provided baseline system is based on a CNN architecture and post-training quantization of parameters. The system is trained using all the available training data, without any specific technique for handling device mismatch, and obtains an overall accuracy of 47.7%, with a log loss of 1.473. The task received 99 submissions from 30 teams, and most of the submitted systems outperformed the baseline. The most used techniques among the submissions were residual networks and weight quantization, with the top systems reaching over 70% accuracy, and log loss under 0.8. The acoustic scene classification task remained a popular task in the challenge, despite the increasing difficulty of the setup.
AlkuperäiskieliEnglanti
OtsikkoProceedings of the 6th Workshop on Detection and Classication of Acoustic Scenes and Events (DCASE 2021)
ToimittajatFrederic Font, Annamaria Mesaros, Daniel P.W. Ellis, Eduardo Fonseca, Magdalena Fuentes, Benjamin Elizalde
Sivut85-89
ISBN (elektroninen) 978-84-09-36072-7
DOI - pysyväislinkit
TilaJulkaistu - 15 marrask. 2021
OKM-julkaisutyyppiA4 Artikkeli konferenssijulkaisussa
TapahtumaDetection and Classication of Acoustic Scenes and Events - , Espanja
Kesto: 15 marrask. 202119 marrask. 2021

Conference

ConferenceDetection and Classication of Acoustic Scenes and Events
Maa/AlueEspanja
Ajanjakso15/11/2119/11/21

Julkaisufoorumi-taso

  • Jufo-taso 0

Sormenjälki

Sukella tutkimusaiheisiin 'Low-complexity acoustic scene classification for multi-device audio: analysis of DCASE 2021 Challenge systems'. Ne muodostavat yhdessä ainutlaatuisen sormenjäljen.

Siteeraa tätä