This paper presents an extension to train end-to-end Context-Aware Transformer Transducer ( CATT ) models by using a simple, yet efficient method of mining hard negative phrases from the latent space of the context encoder. During training, given a reference query, we mine a number of similar phrases using approximate nearest neighbour search. These sampled phrases are then used as negative examples in the context list alongside random and ground truth contextual information. By including approximate nearest neighbour phrases (ANN-P) in the context list, we encourage the learned representation to disambiguate between similar, but not identical, biasing phrases. This improves biasing accuracy when there are several similar phrases in the biasing inventory. We carry out experiments in a large-scale data regime obtaining up to 7% relative word error rate reductions for the contextual portion of test data. We also extend and evaluate CATT approach in streaming applications.

翻译：本文提出了一种扩展方法，用于训练端到端上下文感知Transformer换能器（CATT）模型，该方法通过从上下文编码器的潜在空间中挖掘困难负例短语，既简单又高效。在训练过程中，给定一个参考查询，我们利用近似最近邻搜索挖掘若干相似短语。这些采样的短语随后作为上下文列表中的负例，与随机和真实上下文信息一起使用。通过在上下文列表中纳入近似最近邻短语（ANN-P），我们促使学习到的表示能够区分相似但不相同的偏置短语。当偏置库中存在多个相似短语时，这有助于提升偏置准确性。我们在大规模数据场景下进行了实验，在测试数据的上下文部分获得了高达7%的相对词错误率降低。此外，我们还将CATT方法扩展并评估至流式应用场景。