Acoustic Approaches to Gender and Accent Identification

DeMarco, Andrea (2015) Acoustic Approaches to Gender and Accent Identification. Doctoral thesis, University of East Anglia.

[img]
Preview
PDF
Download (7MB) | Preview

Abstract

There has been considerable research on the problems of speaker and language recognition
from samples of speech. A less researched problem is that of accent recognition. Although this
is a similar problem to language identification, di�erent accents of a language exhibit more
fine-grained di�erences between classes than languages. This presents a tougher problem
for traditional classification techniques. In this thesis, we propose and evaluate a number of
techniques for gender and accent classification. These techniques are novel modifications and
extensions to state of the art algorithms, and they result in enhanced performance on gender
and accent recognition.
The first part of the thesis focuses on the problem of gender identification, and presents a
technique that gives improved performance in situations where training and test conditions are
mismatched.
The bulk of this thesis is concerned with the application of the i-Vector technique to accent
identification, which is the most successful approach to acoustic classification to have emerged
in recent years. We show that it is possible to achieve high accuracy accent identification without
reliance on transcriptions and without utilising phoneme recognition algorithms. The thesis
describes various stages in the development of i-Vector based accent classification that improve
the standard approaches usually applied for speaker or language identification, which are
insu�cient. We demonstrate that very good accent identification performance is possible with
acoustic methods by considering di�erent i-Vector projections, frontend parameters, i-Vector
configuration parameters, and an optimised fusion of the resulting i-Vector classifiers we can
obtain from the same data.
We claim to have achieved the best accent identification performance on the test corpus
for acoustic methods, with up to 90% identification rate. This performance is even better than
previously reported acoustic-phonotactic based systems on the same corpus, and is very close
to performance obtained via transcription based accent identification. Finally, we demonstrate
that the utilization of our techniques for speech recognition purposes leads to considerably
lower word error rates.
Keywords: Accent Identification, Gender Identification, Speaker Identification, Gaussian
Mixture Model, Support Vector Machine, i-Vector, Factor Analysis, Feature Extraction, British
English, Prosody, Speech Recognition.

Item Type: Thesis (Doctoral)
Faculty \ School: Faculty of Science > School of Computing Sciences
Depositing User: Mia Reeves
Date Deposited: 01 Jul 2015 08:49
Last Modified: 01 Jul 2015 08:49
URI: https://ueaeprints.uea.ac.uk/id/eprint/53443
DOI:

Actions (login required)

View Item View Item