Crowdsourced Multilingual Speech Intelligibility Testing
Lechler, Laura, Wojcicki, Kamil
–arXiv.org Artificial Intelligence
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.
arXiv.org Artificial Intelligence
Mar-21-2024
- Country:
- Asia
- China > Shanghai
- Shanghai (0.04)
- South Korea > Incheon
- Incheon (0.04)
- Thailand > Chiang Mai
- Chiang Mai (0.04)
- China > Shanghai
- Europe
- Czechia > South Moravian Region
- Brno (0.04)
- Greece (0.04)
- United Kingdom > England
- Oxfordshire > Oxford (0.04)
- Czechia > South Moravian Region
- North America
- Canada > Quebec
- Montreal (0.04)
- United States
- Florida > Palm Beach County
- Boca Raton (0.04)
- Massachusetts > Middlesex County
- Sudbury (0.04)
- Rhode Island (0.04)
- Florida > Palm Beach County
- Canada > Quebec
- Asia
- Genre:
- Research Report > Experimental Study (1.00)
- Technology: