Personal rare word recognition in end-to-end Automatic Speech Recognition (E2E ASR)
models is a challenge due to the lack of training data. A standard way to address this issue …

Attention-based biasing techniques for end-to-end ASR systems are able to achieve large
accuracy gains without requiring the inference algorithm adjustments and parameter tuning …

Unlike the traditional model, the end-to-end (E2E) ASR model does not require speech
information such as a pronunciation dictionary, and its system is built through a single neural …

Contextual information plays a crucial role in speech recognition technologies and
incorporating it into the end-to-end speech recognition models has drawn immense interest …

Transformer models have demonstrated superior performance across various domains,
including computer vision, natural language processing, and speech recognition. The …

ASR systems in real applications must be adapted on the fly to correctly recognize task-
specific contextual terms, such as contacts, application names and media entities. However …

In this work, we present a model-based approach to improving contextual biasing that
improves quality without drastically increasing model computation during inference …

By incorporating additional contextual information, deep biasing methods have emerged as
a promising solution for speech recognition of personalized words. However, for real-world …

Attention-based contextual biasing approaches have shown significant improvements in the
recognition of generic and/or personal rare-words in End-to-End Automatic Speech …

The recurrent neural network transducer (RNN-T) is a prominent streaming end-to-end
(E2E) ASR technology. In RNN-T, the acoustic encoder commonly consists of stacks of …