Affiliation:
1. Intron Health
2. Masakhane NLP
3. CISPA Helmholtz Center for Information Security
4. AI Saturdays Lagos
5. Karya Inc
6. Mila Quebec AI Institute
7. Lanfrica
8. Ford Motor Company,
9. Lelapa AI
10. McGill University
11. University of Deutso
12. Instituto Politécnico Nacional
13. University of Colorado, Colorado Springs
14. University of Minnesota
Abstract
Abstract
Africa has a very poor doctor-to-patient ratio. At very busy clinics, doctors could see 30+ patients per day—a heavy patient burden compared with developed countries—but productivity tools such as clinical automatic speech recognition (ASR) are lacking for these overworked clinicians. However, clinical ASR is mature, even ubiquitous, in developed nations, and clinician-reported performance of commercial clinical ASR systems is generally satisfactory. Furthermore, the recent performance of general domain ASR is approaching human accuracy. However, several gaps exist. Several publications have highlighted racial bias with speech-to-text algorithms and performance on minority accents lags significantly. To our knowledge, there is no publicly available research or benchmark on accented African clinical ASR, and speech data is non-existent for the majority of African accents. We release AfriSpeech, 200hrs of Pan-African English speech, 67,577 clips from 2,463 unique speakers across 120 indigenous accents from 13 countries for clinical and general domain ASR, a benchmark test set, with publicly available pre-trained models with SOTA performance on the AfriSpeech benchmark.
Subject
Artificial Intelligence,Computer Science Applications,Linguistics and Language,Human-Computer Interaction,Communication
Reference75 articles.
1. Chronic staff shortfalls stifle Africa’s health systems: WHO study — afro.who.int;World Health Organization
2. Supervised domain adaptation for emotion recognition from speech;Abdelwahab,2015
3. Learning nigerian accent embeddings from speech: Preliminary results based on sautidb-naija corpus;Afonja;arXiv preprint arXiv:2112.06199,2021
4. Introduction of digital speech recognition in a specialised outpatient department: A case study;Ahlgrim;BMC Medical Informatics and Decision Making,2016
5. The health workforce status in the WHO African region: Findings of a cross-sectional study;Ahmat;BMJ Global Health,2022