Recent Advances in Voice Identification Technology
A special issue of Applied Sciences (ISSN 2076-3417). This special issue belongs to the section "Acoustics and Vibrations".
Deadline for manuscript submissions: closed (31 March 2021) | Viewed by 610
Special Issue Editors
Interests: the relationships between individual bio-physical characteristics of the head, throat, and larynx; acoustic aspects of speech and auditory perceptions of voices
Interests: rhythm, tempo, pitch, and other aspects of speech prosody; human and machine communication with speech; speaker-specific (indexical) information; voice recognition.
Interests: automatic speaker recognition; human perception of synthetic speech; authentication of audio recordings; authentication of recordings; audio enhancement; speaker comparison; acoustic crime scene reconstructions
Interests: understanding the indexical cues modification in different speaking styles and their implications for human and machine perceptions; automatic speaker recognition techniques; x-vectors; speech synthesis techniques; deep-fake and voice conversion; neural aspects of infants’ voice recognition abilities.
Special Issue Information
Dear Colleagues,
Recent years have seen wide deployment of Automatic Speaker Recognition systems (ASRs) for ensuring information security, for accessing and transferring finance, and in the forensic sector. The greater confidence in, and acceptance of, the technology has in large part arisen from improvements to its accuracy and to its robustness when operating in less-than-ideal conditions. The focus of this Special Issue of Applied Sciences will be on these advances.
We call for research papers on, but not confined to, the following topics:
- advances in the architecture of ASR technology, improvements to algorithms, and development of x-vectors, deep neural networks (DNNs) and beyond;
- relationships between the features utilised by ASRs and those used in more ‘traditional’ voice/speaker comparison casework;
- testing of ASRs to establish performance levels under different operating conditions: levels of noise, reverberation, limited frequency bandwidth speech input, short speech samples, and different voice types;
- use of reference populations of voices and the creation and organisation of voice data-banks; and
- surveys/reviews concerning the use of ASRs in banking and forensic domains.
In addition to the empirical research papers, we would consider including one, or at most two, brief papers addressing ethical and/or legal issues surrounding the use of ASR technology.
Potential authors may, in the first instance, wish to contact the editors directly to discuss their proposed contributions.
Prof. Dr. Peter French
Prof. Dr. Volker Dellwo
Dr. Philip Harrison
Dr. Thayabaran Kathiresan
Guest Editors
Manuscript Submission Information
Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All submissions that pass pre-check are peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 100 words) can be sent to the Editorial Office for announcement on this website.
Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-blind peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Applied Sciences is an international peer-reviewed open access semimonthly journal published by MDPI.
Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 2400 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.
Keywords
- automatic speaker recognition systems (ASRs)
- voice identification
- advances in technology
- x-vectors
- deep neural networks (DNNs)
- resilience to potential inhibitors
- performance testing
- reference populations
- voice data-banks
- banking and forensic applications
- ethical and legal aspects
