AfriNames: Most ASR models "butcher" African Names
Preprint
Abstract
Useful conversational agents must accurately capture named entities to minimize error for downstream tasks, for example, asking a voice assistant to play a track from a certain artist, initiating navigation to a specific location, or documenting a laboratory result for a patient. However, where named entities such as ``Ukachukwu`` (Igbo), ``Lakicia`` (Swahili), or ``Ingabire`` (Rwandan) are spoken, automatic speech recognition (ASR) models' performance degrades significantly, propagating errors to downstream systems. We model this problem as a distribution shift and demonstrate that such model bias can be mitigated through multilingual pre-training, intelligent data augmentation strategies to increase the representation of African-named entities, and fine-tuning multilingual ASR models on multiple African accents. The resulting fine-tuned models show an 81.5\% relative WER improvement compared with the baseline on samples with African-named entities.Keywords
All Related Versions
This publication has 11 references indexed in Scilit:
- End-to-end model for named entity recognition from speech without paired training data2022
- WavLM: Large-Scale Self-Supervised Pre-Training for Full Stack Speech ProcessingIEEE Journal of Selected Topics in Signal Processing, 2022
- HuBERT: Self-Supervised Speech Representation Learning by Masked Prediction of Hidden UnitsIEEE/ACM Transactions on Audio, Speech, and Language Processing, 2021
- MasakhaNER: Named Entity Recognition for African LanguagesTransactions of the Association for Computational Linguistics, 2021
- Improving Named Entity Recognition in Spoken Dialog Systems by Context and Speech Pattern Modeling2021
- Conformer: Convolution-augmented Transformer for Speech Recognition2020
- Racial disparities in automated speech recognitionProceedings of the National Academy of Sciences, 2020
- Towards End-to-End spoken intent recognition in smart home2019
- Personal name in Igbo Culture: A dataset on randomly selected personal names and their statistical analysisData in Brief, 2017
- Using African Names to Identify the Origins of Captives in the Transatlantic Slave Trade: Crowd-Sourcing and the Registers of Liberated Africans, 1808–1862History in Africa, 2013