FluencyBank Timestamped: An Updated Data Set for Disfluency Detection and Automatic Intended Speech Recognition
Our analysis shows that there are gaps in speech recognition and disfluency detection performance between typical speech and speech from PWS. We hope that FluencyBank Timestamped will contribute to more advancements in training robust speech processing models.
Authors
- Emily Mower Provost (ORCID: https://orcid.org/0000-0003-1870-6063)
- Minxue Niu (ORCID: https://orcid.org/0009-0007-8266-9152)
- Amrit Romana (ORCID: https://orcid.org/0009-0005-2360-0732)
- Matthew Perez (ORCID: https://orcid.org/0009-0005-5348-3020)
Institutions
- Google (United States) (US)
- University of Michigan (US)
Publication Details
- Journal
- Journal of Speech Language and Hearing Research
- Published
- 2024-10-08
- DOI
- https://doi.org/10.1044/2024_jslhr-24-00070
- Citations
- 5
- Primary Topic
- Stuttering Research and Treatment
- Type
- article
- Field-Weighted Citation Impact
- 3.20
Funders
- National Science Foundation
- National Institutes of Health
- National Institute on Deafness and Other Communication Disorders