Phonated speech reconstruction using twin mapping models
Loading...
Supplementary material
Other Title
Authors
Sharifzadeh, Hamid
HajiRassouliha, Amir
McLoughlin, I.V.
Ardekani, Iman
Allen, Jacqueline E.
HajiRassouliha, Amir
McLoughlin, I.V.
Ardekani, Iman
Allen, Jacqueline E.
Author ORCID Profiles (clickable)
Degree
Grantor
Date
2015-12
Supervisors
Type
Conference Contribution - Paper in Published Proceedings
Ngā Upoko Tukutuku (Māori subject headings)
Keyword
speech reconstruction
impaired speech
aphonic patients
dysphonic patients
voice production
computational speech reconstruction algorithms
dysphonia
impaired speech
aphonic patients
dysphonic patients
voice production
computational speech reconstruction algorithms
dysphonia
ANZSRC Field of Research Code (2020)
Citation
Sharifzadeh, H. R., HajiRassouliha, A., McLoughlin, I. V., Ardekani, I. T., & Allen, J. E. (2015, December) Phonated Speech Reconstruction Using Twin Mapping Models. IEEE (Ed.), Proceedings of the 15th IEEE International Symposium on Signal Processing and Information Technology (pp.1-6)
Abstract
Computational speech reconstruction algorithms have the ultimate aim of returning natural sounding speech to aphonic and dysphonic individuals. These algorithms can also be used by unimpaired speakers for communicating sensitive or private information. When the glottis loses function due to disease or surgery, aphonic and dysphonic patients retain the power of vocal tract modulation to some degree but they are unable to speak anything more than hoarse whispers without prosthetic aid. While whispering can be seen as a natural and secondary aspect of speech communications for most people, it becomes the primary mechanism of communications for those who have impaired voice production mechanisms, such as laryngectomees.
In this paper, by considering the current limitations of speech reconstruction methods, a novel algorithm for converting whispers to normal speech is proposed and the efficiency of the algorithm is discussed. The proposed algorithm relies upon twin mapping models and makes use of artificially generated whispers (called whisperised speech) to regenerate natural phonated speech from whispers. Through a training-based approach, the mapping models exploit whisperised speech to overcome frame to frame time alignment problem in the speech reconstruction process.
Publisher
IEEE Communications Society
Permanent link
Link to ePress publication
DOI
Copyright holder
IEEE Communications Society
Copyright notice
All rights reserved