Search for collections on Wintec Research Archive

An investigation and comparison of speech recognition software for determining if bird song recordings contain legible human voices

Citation: UNSPECIFIED.

[thumbnail of 2017Hunt_Recognition.pdf] PDF
2017Hunt_Recognition.pdf

Download (338kB)

Abstract

The purpose of this work was to test the effectiveness of using readily available speech recognition API services to determine if recordings of bird song had inadvertently recorded human voices. A mobile phone was used to record a human speaking at increasing distances from the phone in an outside setting with bird song occurring in the background. One of the services was trained with sample recordings nd each service was compared for their ability to return recognized words. The services from Google and IBM performed similarly and the Microsoft service, that allowed training, performed slightly better. However, all three services failed to perform at a level that would enable recordings with recognizable human speech to be deleted in order to maintain full privacy protection.

Item Type: Journal article
Subjects: Q Science > QA Mathematics > QA76 Computer software
Divisions: Schools > Centre for Business, Information Technology and Enterprise > School of Information Technology
Depositing User: Tim Hunt
Date Deposited: 28 Jul 2017 01:38
Last Modified: 21 Jul 2023 04:42
URI: http://researcharchive.wintec.ac.nz/id/eprint/5391

Actions (login required)

View Item
View Item