Crowdsourced Multilingual Speech Intelligibility Testing
Not on the map. Why?
Abstract (arXiv)
With the advent of generative audio features, there is an increasing need for rapid evaluation of their impact on speech intelligibility. Beyond the existing laboratory measures, which are expensive and do not scale well, there has been comparatively little work on crowdsourced assessment of intelligibility. Standards and recommendations are yet to be defined, and publicly available multilingual test materials are lacking. In response to this challenge, we propose an approach for a crowdsourced intelligibility assessment. We detail the test design, the collection and public release of the multilingual speech data, and the results of our early experiments.
Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 10 of its 34 references that are in the map. First posted on arXiv 21 Mar 2024.
Builds on
10 of 34 references.
References · 10
- 2022Speech Enhancement and Dereverberation with Diffusion-based Generative Modelscited by 195
- 2022StoRM: A Diffusion-based Stochastic Regeneration Model for Speech Enhancement and Dereverberationcited by 105
- 2023ICASSP 2023 Deep Noise Suppression Challengecited by 62
- 2020An Open source Implementation of ITU-T Recommendation P.808 with Validationcited by 27
- 2021Objective Measures of Perceptual Audio Quality Reviewed: An Evaluation of Their Application Domain Dependencecited by 14
- 2021Speech Quality Assessment in Crowdsourcing: Comparison Category Rating Methodcited by 4
- 2022Real-Time Packet Loss Concealment With Mixed Generative and Predictive Modelcited by 4
- 2021Comparison of remote experiments using crowdsourcing and laboratory experiments on speech intelligibilitycited by 1
- 2022Effective data screening technique for crowdsourced speech intelligibility experiments: Evaluation with IRM-based speech enhancementcited by 1
- 2023On Crowdsourcing-design with Comparison Category Rating for Evaluating Speech Enhancement Algorithmscited by 1
Built on by
Not cited yet.