Industrial research into the reduction of biases in foundational Automatic Speech Recognition models.

点击翻译按钮获取中文摘要

**Industrial research into the reduction of biases in foundational Automatic Speech Recognition models.**This research will focus on foundational Automatic Speech Recognition (ASR) models like OpenAI's Whisper and explore the biases in them in relation to linguistic groups in the UK.By identifying and mitigating the biases in these foundation ASR models that leverage Natural Language Processing (NLP), this research paves the way for more equitable AI, AI that is more socially responsible, trustworthy, and therefore widely adopted.