Benchmarking and Research Infrastructures: Evaluating Dutch Automatic Speech Recognition

Research output: Chapter in Book/Report/Conference proceedingConference contributionAcademicpeer-review

30 Downloads (Pure)

Abstract

In this paper we present the setup and results of a Dutch Open Speech Recognition Benchmark strategy, initiated in the course of use cases in three research infrastructure projects in The Netherlands, to help scholars, infrastructure providers, and speech researchers make informed choices about which speech recognition engines, configurations and models to use, to facilitate or to improve upon. The obtained results are a tangible starting point to expand collaboration and optimize the coverage of the speech types and conditions addressed in the benchmark.
Original languageEnglish
Title of host publicationCLARIN Annual Conference Proceedings
EditorsVincent Vandeghinste, Thalassia Kontino
Pages140-143
Number of pages4
Publication statusPublished - 16 Oct 2024
EventCLARIN Annual Conference 2024 - Hotel Barceló Sants, Barcelona, Spain
Duration: 15 Oct 202417 Oct 2024
https://www.clarin.eu/event/2024/clarin-annual-conference-2024

Conference

ConferenceCLARIN Annual Conference 2024
Abbreviated titleCLARIN 2024
Country/TerritorySpain
CityBarcelona
Period15/10/2417/10/24
Internet address

Keywords

  • Research infrastructure
  • Benchmark
  • Dutch
  • Automatic Speech Recognition

Fingerprint

Dive into the research topics of 'Benchmarking and Research Infrastructures: Evaluating Dutch Automatic Speech Recognition'. Together they form a unique fingerprint.

Cite this