Toward Fairness in Speech Recognition: Discovery and mitigation of performance disparities

Abstract

As for other forms of AI, speech recognition has recently been examined with respect to performance disparities across different user cohorts. One approach to achieve fairness in speech recognition is to (1) identify speaker cohorts that suffer from subpar performance and (2) apply fairness mitigation measures targeting the cohorts discovered. In this paper, we report on initial findings with both discovery and mitigation of performance disparities using data from a product-scale AI assistant speech recognition system. We compare cohort discovery based on geographic and demographic information to a more scalable method that groups speakers without human labels, using speaker embedding technology. For fairness mitigation, we find that oversampling of underrepresented cohorts, as well as modeling speaker cohort membership by additional input variables, reduces the gap between top- and bottom-performing cohorts, without deteriorating overall recognition accuracy.

Proc. Interspeech 2022

References in corpus (5)

• Sequence Transduction with Recurrent Neural Networks
• Does Object Recognition Work for Everyone?
• Saving Face: Investigating the Ethical Concerns of Facial Recognition Auditing
• Quantifying Bias in Automatic Speech Recognition
• Towards Measuring Fairness in Speech Recognition: Casual Conversations Dataset Transcriptions

Cited by in corpus (2)

• Spoken Stereoset: On Evaluating Social Bias Toward Speaker in Speech Large Language Models
• Cross-utterance ASR Rescoring with Graph-based Label Propagation