The "Sprekend Nederland" project and its application to accent location

TL;DR

This paper details the Sprekend Nederland project’s data collection and explores its application in automatic accent location, aiming to identify speaker origins based on accent features.

Contribution

It introduces a large-scale Dutch speech dataset and discusses methods and metrics for automatic accent location, advancing research in regional accent identification.

Findings

Potential for accurate accent location based on collected data

Evaluation metrics for assessing accent location performance

Discussion of descriptive approaches for accent characterization

Abstract

This paper describes the data collection effort that is part of the project Sprekend Nederland (The Netherlands Talking), and discusses its potential use in Automatic Accent Location. We define Automatic Accent Location as the task to describe the accent of a speaker in terms of the location of the speaker and its history. We discuss possible ways of describing accent location, the consequence these have for the task of automatic accent location, and potential evaluation metrics.