End-to-end Contextual Speech Recognition Using Class Language Models And A Token Passing Decoder

Abstract

End-to-end modeling (E2E) of automatic speech recognition (ASR) blends all the components of a traditional speech recognition system into a unified model. Although it simplifies training and decoding pipelines, the unified model is hard to adapt when mismatch exists between training and test data. In this work, we focus on contextual speech recognition, which is particularly challenging for E2E models because it introduces significant mismatch between training and test data. To improve the performance in the presence of complex contextual information, we propose to use class-based language models(CLM) that can populate the classes with contextdependent information in real-time. To enable this approach to scale to a large number of class members and minimize search errors, we propose a token passing decoder with efficient token recombination for E2E systems for the first time. We evaluate the proposed system on general and contextual ASR, and achieve relative 62% Word Error Rate(WER) re

Stats

• citations29
• S2 citations—
• github stars0
• HF likes0
• heat score11.08
• arxiv keychen2018end

Related papers

• Deep Context: End-to-end Contextual Speech Recognition (2018)15.57
• Cif-based Collaborative Decoding For End-to-end Contextual Speech Recognition (2020)9.76
• End-to-end Speech Recognition Contextualization With Large Language Models (2023)0.00
• Integrating Pre-trained Speech And Language Models For End-to-end Speech Recognition (2023)0.00
• Multi-task Language Modeling For Improving Speech Recognition Of Rare Words (2020)8.35
• Advanced Long-context End-to-end Speech Recognition Using Context-expanded Transformers (2021)10.07
• Two-pass End-to-end Speech Recognition (2019)13.97
• Enhancing Large Language Model-based Speech Recognition By Contextualization For Rare And Ambiguous Words (2024)0.00