An empirical investigation into audio pipeline approaches for\n classifying bird species

Résumé

This paper is an investigation into aspects of an audio classification\npipeline that will be appropriate for the monitoring of bird species on edges\ndevices. These aspects include transfer learning, data augmentation and model\noptimization. The hope is that the resulting models will be good candidates to\ndeploy on edge devices to monitor bird populations. Two classification\napproaches will be taken into consideration, one which explores the\neffectiveness of a traditional Deep Neural Network(DNN) and another that makes\nuse of Convolutional layers.This study aims to contribute empirical evidence of\nthe merits and demerits of each approach.\n

Citer ce document

Accès au document

Ce document est hébergé sur son dépôt institutionnel d'origine.

Auteur(s)

Statistiques

Consultations : 1

Téléchargements : 0