Abstract
Commercial Automatic Speech Recognition (ASR) systems tend to show systemic predictive bias for marginalised speaker/user groups. We highlight the need for an interdisciplinary and context-sensitive approach to documenting this bias incorporating perspectives and methods from sociolinguistics, speech & language technology and human-computer interaction in the context of a case study. We argue evaluation of ASR systems should be disaggregated by speaker group, include qualitative error analysis, and consider user experience in a broader sociolinguistic and social context.- Anthology ID:
- 2021.hcinlp-1.6
- Volume:
- Proceedings of the First Workshop on Bridging Human–Computer Interaction and Natural Language Processing
- Month:
- April
- Year:
- 2021
- Address:
- Online
- Venue:
- HCINLP
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 34–40
- Language:
- URL:
- https://aclanthology.org/2021.hcinlp-1.6
- DOI:
- Cite (ACL):
- Nina Markl and Catherine Lai. 2021. Context-sensitive evaluation of automatic speech recognition: considering user experience & language variation. In Proceedings of the First Workshop on Bridging Human–Computer Interaction and Natural Language Processing, pages 34–40, Online. Association for Computational Linguistics.
- Cite (Informal):
- Context-sensitive evaluation of automatic speech recognition: considering user experience & language variation (Markl & Lai, HCINLP 2021)
- PDF:
- https://preview.aclanthology.org/ingestion-script-update/2021.hcinlp-1.6.pdf