Improving Synthetic Data Training for Contextual Biasing Models with a Keyword-Aware Cost Function
This incremental improvement addresses rare word recognition in automatic speech recognition systems.
The paper tackled overfitting in contextual biasing models for rare word recognition by proposing a keyword-aware loss function, reducing word error rate from 29.71% to 11.81% on the NSC Part 2 test set.
Rare word recognition can be improved by adapting ASR models to synthetic data that includes these words. Further improvements can be achieved through contextual biasing, which trains and adds a biasing module into the model architecture to prioritize rare words. While training the module on synthetic rare word data is more effective than using non-rare-word data, it can lead to overfitting due to artifacts in the synthetic audio. To address this, we enhance the TCPGen-based contextual biasing approach and propose a keyword-aware loss function that additionally focuses on biased words when training biasing modules. This loss includes a masked cross-entropy term for biased word prediction and a binary classification term for detecting biased word positions. These two terms complementarily support the decoding of biased words during inference. By adapting Whisper to 10 hours of synthetic data, our method reduced the word error rate on the NSC Part 2 test set from 29.71% to 11.81%.