This paper introduces a novel Token-and-Duration Transducer (TDT) architecture for
sequence-to-sequence tasks. TDT extends conventional RNN-Transducer architectures by …

In recent years, Large Language Models (LLMs) have garnered significant attention from the
research community due to their exceptional performance and generalization capabilities. In …

In real-world applications, users often require both translations and transcriptions of speech
to enhance their comprehension, particularly in streaming scenarios where incremental …

We explore contextual biasing with Large Language Models (LLMs) to enhance Automatic
Speech Recognition (ASR) in second-pass rescoring. Our approach introduces the …

Deep biasing for the Transducer can improve the recognition performance of rare words or
contextual entities, which is essential in practical applications, especially for streaming …

The attention-based deep contextual biasing method has been demonstrated to effectively
improve the recognition performance of end-to-end automatic speech recognition (ASR) …

The vast majority of inference time for RNN Transducer (RNN-T) models today is spent on
decoding. Current state-of-the-art RNN-T decoding implementations leave the GPU idle …

Recently, Conformer as a backbone network for end-to-end automatic speech recognition
achieved state-of-the-art performance. The Conformer block leverages a self-attention …

Contextualized end-to-end automatic speech recognition has been an active research area,
with recent efforts focusing on the implicit learning of contextual phrases based on the final …

In this paper, we propose a Guided Attention (GA) auxiliary training loss, which improves the
effectiveness and robustness of automatic speech recognition (ASR) contextual biasing …