Back to search

University of Birmingham

Speech analysis using very low-dimensional bottleneck features and phone-class dependent neural networks

Abstract

dc:description.abstract

The first part of this thesis focuses on very low-dimensional bottleneck features (BNFs), extracted from deep neural networks (DNNs) for speech analysis and recognition. Very low-dimensional BNFs are analysed in terms of their capability of representing speech and their suitability for modelling speech dynamics. Nine-dimensional BNFs obtained from a phone discrimination DNN are shown to give comparable phone recognition accuracy to 39-dimensional MFCCs, and an average of 34% higher phone recognition accuracy than formant-based features of the same dimensions. They also preserve the trajectory continuity well and thus hold promise for modelling speech dynamics. Visualisations and interpretations of the BNFs are presented, with phonetically motivated studies of the strategies that DNNs employ to create these features. The relationships between BNF representations resulting from different initialisations of DNNs are explored. The second part of this thesis considers BNFs from the perspective of feature extraction. It is motivated by the observation that different types of speech sounds lend themselves to different acoustic analysis, and that the mapping from spectra-in-context to phone posterior probabilities implemented by the DNN is a continuous approximation to a discontinuous function. This suggests that it may be advantageous to replace the single DNN with a set of phone class dependent DNNs. In this case, the appropriate mathematical structure is a manifold. It is shown that this approach leads to significant improvements in frame level phone classification accuracy.

Degree

thesis:*
Name dc:type.qualificationname
d_ph
Level dc:type.qualificationlevel
d_ph
Grantor dc:publisher.institution
University of Birmingham
Year dc:date.issued
2018

Author and committee

dc:creator, dc:contributor.*
Author dc:creator
  • Bai, Linxue

Subjects

dc:subject × 1

Rights

Language dc:language.dcterms_iso639_2
eng

Chain of custody

source
Harvested from
University of Birmingham
Base URL
etheses.bham.ac.uk/cgi/oai2
Last updated
2026-11-19
Source record
OAI-PMH GetRecord
citation

Bai, Linxue. Speech analysis using very low-dimensional bottleneck features and phone-class dependent neural networks. d_ph thesis, University of Birmingham, 2018.