Cross-utterance ASR Rescoring with Graph-based Label Propagation
This provides a low-cost solution for mitigating majoritarian bias in ASR systems without requiring new domain- or accent-specific models.
The paper tackles ASR performance and fairness issues by proposing a graph-based label propagation approach for N-best hypothesis rescoring that leverages cross-utterance acoustic similarity, demonstrating consistent improvements on the VCTK dataset and enhanced fairness across speaker groups with different accents.
We propose a novel approach for ASR N-best hypothesis rescoring with graph-based label propagation by leveraging cross-utterance acoustic similarity. In contrast to conventional neural language model (LM) based ASR rescoring/reranking models, our approach focuses on acoustic information and conducts the rescoring collaboratively among utterances, instead of individually. Experiments on the VCTK dataset demonstrate that our approach consistently improves ASR performance, as well as fairness across speaker groups with different accents. Our approach provides a low-cost solution for mitigating the majoritarian bias of ASR systems, without the need to train new domain- or accent-specific models.