Toward Fairness in Speech Recognition: Discovery and mitigation of performance disparities
This addresses fairness issues in speech recognition for diverse user groups, but it is incremental as it builds on existing methods for bias mitigation.
The paper tackled performance disparities in speech recognition by discovering underperforming speaker cohorts and applying mitigation measures, finding that oversampling underrepresented cohorts and modeling cohort membership reduced the gap between top- and bottom-performing cohorts without harming overall accuracy.
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.