Deep neural networks in speech recognition
Abstract/Contents
- Abstract
- Spoken language is an increasingly pervasive interface choice as computing devices permeate many aspects of daily life. Automatically understanding spoken language poses significant challenges because it requires both converting a speech signal into words and extracting meaning from the words themselves. Spoken language understanding tasks can roughly be broken into distinct components which perform (1) low-level processing of the audio signal, (2) speech transcription, and (3) natural language understanding. We describe approaches to improving individual components for each sub-task associated with spoken language understanding. Our methods primarily rely on machine-learning-based approaches to replace hand-engineered approaches and consistently find that learning from data with minimal assumptions about a problem results in improved performance. In particular, we focus on neural network approaches to problems. Neural networks have seen a recent resurgence of interest thanks to their ability to scale to learn increasingly complex functions when more data becomes available. Neural networks have recently driven tremendous progress in the field of computer vision, where many tasks easily translate into classification and regression problems. In spoken language understanding, however, it is more difficult to define tasks which are easily formalized into problems for a neural network to solve. Our work integrates with these complex systems and shows that, like in computer vision, neural networks can significantly improve spoken language understanding systems.
Description
Type of resource | text |
---|---|
Form | electronic; electronic resource; remote |
Extent | 1 online resource. |
Publication date | 2015 |
Issuance | monographic |
Language | English |
Creators/Contributors
Associated with | Maas, Andrew Lee |
---|---|
Associated with | Stanford University, Department of Computer Science. |
Primary advisor | Ng, Andrew Y, 1976- |
Thesis advisor | Ng, Andrew Y, 1976- |
Thesis advisor | Jurafsky, Dan, 1962- |
Thesis advisor | Liang, Percy |
Advisor | Jurafsky, Dan, 1962- |
Advisor | Liang, Percy |
Subjects
Genre | Theses |
---|
Bibliographic information
Statement of responsibility | Andrew Lee Maas. |
---|---|
Note | Submitted to the Department of Computer Science. |
Thesis | Thesis (Ph.D.)--Stanford University, 2015. |
Location | electronic resource |
Access conditions
- Copyright
- © 2015 by Andrew Lee Maas
- 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...