Page 1 |
Save page Remove page | Previous | 1 of 163 | Next |
|
small (250x250 max)
medium (500x500 max)
Large (1000x1000 max)
Extra Large
large ( > 500x500)
Full Resolution
All (PDF)
|
This page
All
|
HIERARCHICAL METHODS IN AUTOMATIC
PRONUNCIATION EVALUATION
by
Joseph Tepperman
A Dissertation Presented to the
FACULTY OF THE GRADUATE SCHOOL
UNIVERSITY OF SOUTHERN CALIFORNIA
In Partial Fulfillment of the
Requirements for the Degree
DOCTOR OF PHILOSOPHY
(ELECTRICAL ENGINEERING)
August 2009
Copyright 2009 Joseph Tepperman
Object Description
| Title | Hierarchical methods in automatic pronunciation evaluation |
| Author | Tepperman, Joseph |
| Author email | tepperma@usc.edu; joe.tepperman@gmail.com |
| Degree | Doctor of Philosophy |
| Document type | Dissertation |
| Degree program | Electrical Engineering |
| School | Viterbi School of Engineering |
| Date defended/completed | 2009-05-04 |
| Date submitted | 2009 |
| Restricted until | Unrestricted |
| Date published | 2009-06-16 |
| Advisor (committee chair) | Narayanan, Shrikanth S. |
| Advisor (committee member) |
Mendel, Jerry M. Goldstein, Louis M. |
| Abstract | Technology that can automatically categorize pronunciations and estimate scores of pronunciation quality has many potential applications, most notably for second-language learners interested in practicing their pronunciation along with a machine tutor, or for automating the standard assessments elementary school teachers use to measure a child's emerging reading skills. The many sources of variability in speech and the subjective perception of pronunciation make this a complex problem. Linguistic hierarchies - in speech production, perception, and prosodic sturcture -- help to conceive of the variability as existing on multiple simultaneous scales of representation, and offer an explanatory order of precedence to those scales. These theories are beginning to gain widespread attention and use in traditional speech recognition, but experimenters in pronunciation evaluation have been slow to embrace them. This work proposes using theories of hierarchical structure in speech to inform a chosen computational framework and scale of analysis when performing automatic pronunciation evaluation, on the assumption that they will offer improvements over non-hierarchical methods and can be used to rate pronunciation with performance comparable to that of inter-human agreement.; Three example applications here illustrate novel hierarchical approaches over three different standard scales of analysis -- the phoneme, the word, and the phrase. Each one makes use of hierarchical knowledge in at least two ways. First, the acoustic models for evaluation are defined on time-scales below the one of interest (similar to the common practice of using strings of phoneme models to represent words in speech recognition), based on a nested conception of parallel linguistic scales. Then recognition results obtained from these models are aggregated in an ordered structure appropriate to the task and using a computational framework best suited to instantiate the hierarchy. Results show statistically significant improvements over baseline methods that do not use these novel time-scales for modeling variability nor make use of a structured hierarchy in combining the cues derived from those models. |
| Keyword | automatic speech recognition; pronunciation evaluation |
| Language | English |
| Part of collection | University of Southern California dissertations and theses |
| Publisher (of the original version) | University of Southern California |
| Place of publication (of the original version) | Los Angeles, California |
| Publisher (of the digital version) | University of Southern California. Libraries |
| Provenance | Electronically uploaded by the author |
| Type | texts |
| Legacy record ID | usctheses-m2306 |
| Contributing entity | University of Southern California |
| Rights | Tepperman, Joseph |
| Repository name | Libraries, University of Southern California |
| Repository address | Los Angeles, California |
| Repository email | cisadmin@dots.usc.edu |
| Filename | etd-Tepperman-2925 |
| Archival file | uscthesesreloadpub_Volume56/etd-Tepperman-2925.pdf |
Description
| Title | Page 1 |
| Contributing entity | University of Southern California |
| Repository email | cisadmin@dots.usc.edu |
| Full text | HIERARCHICAL METHODS IN AUTOMATIC PRONUNCIATION EVALUATION by Joseph Tepperman A Dissertation Presented to the FACULTY OF THE GRADUATE SCHOOL UNIVERSITY OF SOUTHERN CALIFORNIA In Partial Fulfillment of the Requirements for the Degree DOCTOR OF PHILOSOPHY (ELECTRICAL ENGINEERING) August 2009 Copyright 2009 Joseph Tepperman |
