[PDF][PDF] Contextual Biasing with Confidence-based Homophone Detector for Mandarin End-to-End Speech Recognition
Deep biasing methods and shallow fusion methods have been demonstrated to improve the
performance of end-to-end ASR effectively. However, accurate recognition often becomes …
performance of end-to-end ASR effectively. However, accurate recognition often becomes …
[PDF][PDF] Contextualized speech recognition: rethinking second-pass rescoring with generative large language models
Abstract Automatic Speech Recognition (ASR) systems have witnessed notable
advancements in recent years. Contextualized ASR tasks require recognizing speech not as …
advancements in recent years. Contextualized ASR tasks require recognizing speech not as …
An efficient text augmentation approach for contextualized Mandarin speech recognition
N Zheng, X Wan, K Liu, Z Du, Z Huan - arXiv preprint arXiv:2406.09950, 2024 - arxiv.org
Although contextualized automatic speech recognition (ASR) systems are commonly used to
improve the recognition of uncommon words, their effectiveness is hindered by the inherent …
improve the recognition of uncommon words, their effectiveness is hindered by the inherent …
[PDF][PDF] Improving Speech Recognition with Prompt-based Contextualized ASR and LLM-based Re-predictor
NMT Anh, TH Sy - isca-archive.org
In recent years, advancements in automatic speech recognition (ASR) systems have led to
their widespread use in applications such as call center bots and virtual assistants …
their widespread use in applications such as call center bots and virtual assistants …