Automatic Speech Recognition (ASR) still face challenges when recognizing time-variant rare-phrases. Contextual biasing (CB) modules bias ASR model towards such contextually-relevant phrases. During training, a list of biasing phrases are selected from a large pool of phrases following a sampling strategy. In this work we firstly analyse different sampling strategies to provide insights into the training of CB for ASR with correlation plots between the bias embeddings among various training stages. Secondly, we introduce a neighbourhood attention (NA) that localizes self attention (SA) to the nearest neighbouring frames to further refine the CB output. The results show that this proposed approach provides on average a 25.84% relative WER improvement on LibriSpeech sets and rare-word evaluation compared to the baseline.

翻译：自动语音识别（ASR）在识别时变罕见短语时仍面临挑战。上下文偏置（CB）模块使ASR模型偏向于此类上下文相关的短语。训练过程中，从大量短语池中按照采样策略选取一组偏置短语。本研究首先分析不同采样策略，通过绘制各训练阶段偏置嵌入之间的相关性图，为ASR中CB的训练提供洞见。其次，我们引入邻域注意力（NA）机制，将自注意力（SA）限制在最近邻帧，以进一步优化CB输出。结果表明，与基线相比，该方法在LibriSpeech数据集和罕见词评估上平均实现了25.84%的相对词错误率（WER）改进。