Language model domain adaptation for automatic speech recognition systems
This research addresses the language model (LM) domain mismatch problem in automatic speech recognition (ASR) systems. The ASR systems rely on LMs to constrain its recognition output to linguistically correct hypotheses. While LMs significantly improve the linguistic competence of ASR, they are high...
Saved in:
Main Author: | Khassanov, Yerbolat |
---|---|
Other Authors: | Chng Eng Siong |
Format: | Thesis-Doctor of Philosophy |
Language: | English |
Published: |
Nanyang Technological University
2020
|
Subjects: | |
Online Access: | https://hdl.handle.net/10356/141323 |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Institution: | Nanyang Technological University |
Language: | English |
Similar Items
-
Development of a cortex processor based embedded system
by: Khassanov, Yerbolat.
Published: (2012) -
Deploying automatic speech recognition system for scalability, reliability, and security with Kubernetes
by: Tjandy Putra
Published: (2023) -
Facial expression recognition in the spatio-temporal domain
by: Xiang, Tuo Wen
Published: (2011) -
Automatic video assistant based on speech recognition and natural language processing
by: Zhou, Kaiyu
Published: (2024) -
Data-efficient domain adaptation for pretrained language models
by: Guo, Xu
Published: (2023)