Improving Neural Biasing for Contextual Speech Recognition by Early Context Injection and Text Perturbation

R Huang, M Yarmohammadi, S Khudanpur… - arXiv preprint arXiv …, 2024 - arxiv.org
Existing research suggests that automatic speech recognition (ASR) models can benefit
from additional contexts (eg, contact lists, user specified vocabulary). Rare words and …

Chain-of-Thought Prompting for Speech Translation

K Hu, Z Chen, CHH Yang, P Żelasko… - arXiv preprint arXiv …, 2024 - arxiv.org
Large language models (LLMs) have demonstrated remarkable advancements in language
understanding and generation. Building on the success of text-based LLMs, recent research …

[PDF][PDF] Contextual Biasing Speech Recognition in Speech-enhanced Large Language Model

X Gong, A Lv, Z Wang, Y Qian - Proc. Interspeech 2024, 2024 - isca-archive.org
Recently, the rapid advancements in audio-and speechenhanced large language models
(SpeechLLMs), such as Qwen-Audio and SALMONN, have significantly propelled automatic …

Fast Context-Biasing for CTC and Transducer ASR models with CTC-based Word Spotter

A Andrusenko, A Laptev, V Bataev, V Lavrukhin… - arXiv preprint arXiv …, 2024 - arxiv.org
Accurate recognition of rare and new words remains a pressing problem for contextualized
Automatic Speech Recognition (ASR) systems. Most context-biasing methods involve …

Improving Domain-Specific ASR with LLM-Generated Contextual Descriptions

J Suh, I Na, W Jung - arXiv preprint arXiv:2407.17874, 2024 - arxiv.org
End-to-end automatic speech recognition (E2E ASR) systems have significantly improved
speech recognition through training on extensive datasets. Despite these advancements …

ConEC: Earnings call dataset with real-world contexts for benchmarking contextual speech recognition

R Huang, M Yarmohammadi, J Trmal… - Proceedings of the …, 2024 - aclanthology.org
Knowing the particular context associated with a conversation can help improving the
performance of an automatic speech recognition (ASR) system. For example, if we are …

[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 …