Improving Contextual Biasing with Text Injection

Citations Over TimeTop 19% of 2023 papers

Abstract

In this work, we present a model-based approach to improving contextual biasing that improves quality without drastically increasing model computation during inference. Specifically, we look at injecting text data during training which is representative of contextually-relevant context that will be seen at inference, using a modality-matching text injection method known as JOIST. As JOIST injects text data directly into the E2E model, there is no additional model computation during inference, which is a big difference compared to most model-based biasing techniques. We find that our proposed approach, when combined with an FST-based context model, improves recognition of contacts between 5–15% relative.

Related Papers

• → Estimating the Level of Inference Using an Order-Mimic Agent(2022)1 cited
• → Inference on the New Keynesian Phillips Curve with Very Many Instrumental Variables(2021)1 cited
• → Maximum Likelihood(2004)