By incorporating additional contextual information, deep biasing methods have emerged as a promising solution for speech recognition of personalized words. However, for real-world voice assistants, always biasing on such personalized words with high prediction scores can significantly degrade the performance of recognizing common words. To address this issue, we propose an adaptive contextual biasing method based on Context-Aware Transformer Transducer (CATT) that utilizes the biased encoder and predictor embeddings to perform streaming prediction of contextual phrase occurrences. Such prediction is then used to dynamically switch the bias list on and off, enabling the model to adapt to both personalized and common scenarios. Experiments on Librispeech and internal voice assistant datasets show that our approach can achieve up to 6.7% and 20.7% relative reduction in WER and CER compared to the baseline respectively, mitigating up to 96.7% and 84.9% of the relative WER and CER increase for common cases. Furthermore, our approach has a minimal performance impact in personalized scenarios while maintaining a streaming inference pipeline with negligible RTF increase.

翻译：通过整合额外的上下文信息，深度偏置方法已成为个性化词语语音识别的有前景解决方案。然而，对于实际语音助手而言，持续对这类高预测分数的个性化词语施加偏置会显著降低常见词语的识别性能。针对此问题，我们提出一种基于上下文感知Transformer Transducer（CATT）的自适应上下文偏置方法，该方法利用偏置后的编码器和预测器嵌入来对流式上下文短语的出现进行预测。该预测随后用于动态切换偏置列表的启用与禁用，使模型能够同时适应个性化场景与常见场景。在Librispeech和内部语音助手数据集上的实验表明，与基线相比，我们的方法在WER和CER上分别实现了高达6.7%和20.7%的相对降低，并分别缓解了常见场景中96.7%和84.9%的WER与CER相对增长。此外，我们的方法在保持流式推理流水线且RTF增量可忽略不计的同时，对个性化场景的性能影响极小。