Skip to content
image post
White papers

Online Adaptation of Language Models for Speech Recognition

April 16, 2024

Share with:


Authors: Dang Hoang Vu, Van Huy Nguyen, Phuong Le-Hong

Abstract: Hybrid models of speech recognition combine a neural acoustic model with a language model, which rescores the output of the acoustic model to find the most linguistically likely transcript. Consequently the language model is of key importance in both open and domain specific speech recognition and much work has been done in adapting the language model to the speech input. We present an efficient pipeline for hybrid speech recognition where a domain-specific language model is selected for each utterance based on the result of domain classification. Experiments on public speech recognition datasets in the Vietnamese language show improvements in accuracy over the baseline speech recognition model for little increase in running time.

Published in: International Conference on Computer Recognition Systems, 08 May 2019

Download now

Do you need a workthrough of our platform? Let us know

    Related Posts

    Get ahead with AI-powered technology updates!

    Subscribe now to our newsletter for exclusive insights, expert analysis, and cutting-edge developments delivered straight to your inbox!