Hidden conditional random fields for speech recognition
Abstract/Contents
- Abstract
- This thesis investigates using a new graphical model, hidden conditional random fields (HCRFs), for speech recognition. Conditional random fields (CRFs) are discriminative sequence models that have been successfully applied to several tasks in text processing, such as named entity recognition. Recently, there has been increasing interest in applying CRFs to speech recognition due to the similarity between speech and text processing. HCRFs are CRFs augmented with hidden variables that are capable of representing the dynamic changes and variations in speech signals. HCRFs also have the ability to incorporate correlated features from both speech signals and text without making strong independence assumptions among them. This thesis presents my current research on applying HCRFs to speech recognition and HCRFs' potential to replace the current hidden Markov model (HMM) for acoustic modeling. Experimental results of phone classification, phone recognition, and speaker adaptation are presented and discussed. Our monophone HCRFs outperform both maximum mutual information estimation (MMIE) and minimum phone error (MPE) trained HMMs and achieve the-start-of-the-art performance in TIMIT phone classification and recognition tasks. We also show how to jointly train acoustic models and language models in HCRFs, which shows improvement in the results. Maximum a posterior (MAP) and maximum conditional likelihood linear regression (MCLLR) successfully adapt speaker-independent models to speaker-dependent models with a small amount of adaptation data for HCRF speaker adaptation. Finally, we explore adding gender and dialect features for phone recognition, and experimental results are presented.
Description
| Type of resource | text |
|---|---|
| Form | electronic; electronic resource; remote |
| Extent | 1 online resource. |
| Publication date | 2010 |
| Issuance | monographic |
| Language | English |
Creators/Contributors
| Associated with | Sung, Yun-Hsuan |
|---|---|
| Associated with | Stanford University, Department of Electrical Engineering |
| Primary advisor | Jurafsky, Dan, 1962- |
| Thesis advisor | Jurafsky, Dan, 1962- |
| Thesis advisor | Gray, Robert M, 1943- |
| Thesis advisor | Manning, Christopher D |
| Advisor | Gray, Robert M, 1943- |
| Advisor | Manning, Christopher D |
Subjects
| Genre | Theses |
|---|
Bibliographic information
| Statement of responsibility | Yun-Hsuan Sung. |
|---|---|
| Note | Submitted to the Department of Electrical Engineering. |
| Thesis | Ph.D. Stanford University 2010 |
| Location | electronic resource |
Access conditions
- Copyright
- © 2010 by Yun-Hsuan Sung
- License
- This work is licensed under a Creative Commons Attribution Non Commercial 3.0 Unported license (CC BY-NC).
Also listed in
Loading usage metrics...