Improving ASR Contextual Biasing with Guided Attention

J Tang, K Kim, S Shon, F Wu… - ICASSP 2024-2024 IEEE …, 2024 - ieeexplore.ieee.org
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 …

Hierarchical attention-based contextual biasing for personalized speech recognition using neural transducers

S Tong, P Harding, S Wiesler - 2023 IEEE Automatic Speech …, 2023 - ieeexplore.ieee.org
Although end-to-end (E2E) automatic speech recognition (ASR) systems excel in general
tasks, they frequently struggle with accurately recognizing personal rare words. Leveraging …

An Adapter-Based Unified Model for Multiple Spoken Language Processing Tasks

V Suresh, S Aït-Mokhtar, C Brun… - ICASSP 2024-2024 …, 2024 - ieeexplore.ieee.org
Self-supervised learning models have revolutionized the field of speech processing.
However, the process of fine-tuning these models on downstream tasks requires substantial …

[HTML][HTML] Model-internal slot-triggered biasing for domain expansion in neural transducer ASR models

E Lu, P Harding, KM Sathyendra, S Tong, X Fu, J Liu… - 2023 - amazon.science
Personal rare word recognition is an important yet challenging task for end-to-end speech
recognition. Contextual biasing has demonstrated success in tackling this problem. Though …