prikaz prve stranice dokumenta Online speaker de-identification using voice transformation
  Download
PDF 192.91 KB
Scientific paper - Original scientific paper
Online speaker de-identification using voice transformation
In: BiForD - Biometrics & Forensics & De-identification and Privacy Protection. IEEE, 2014. pp. 39-41. https://doi.org/10.1109/MIPRO.2014.6859761
Pobar, Miran; Ipšić, Ivo

Cite this document

Pobar, M. & Ipšić, I. (2014). Online speaker de-identification using voice transformation. BiForD - Biometrics & Forensics & De-identification and Privacy Protection (pp. 39-41). IEEE. doi: 10.1109/MIPRO.2014.6859761

Pobar, Miran and Ivo Ipšić. "Online speaker de-identification using voice transformation." BiForD - Biometrics & Forensics & De-identification and Privacy Protection, IEEE, 2014, pp. 39-41. https://urn.nsk.hr/urn:nbn:hr:195:107422

Pobar, Miran and Ivo Ipšić. "Online speaker de-identification using voice transformation." In BiForD - Biometrics & Forensics & De-identification and Privacy Protection, 39-41. IEEE, 2014. Accessed 2024 December 19. https://urn.nsk.hr/urn:nbn:hr:195:107422

Pobar, M. and Ipšić, I. (2014) 'Online speaker de-identification using voice transformation', BiForD - Biometrics & Forensics & De-identification and Privacy Protection, IEEE, pp. 39-41. Available at: https://urn.nsk.hr/urn:nbn:hr:195:107422 (Accessed 19 December 2024)

Pobar M, Ipšić I. Online speaker de-identification using voice transformation. BiForD - Biometrics & Forensics & De-identification and Privacy Protection. IEEE; 2014. Pp. 39-41. [cited 2024 December 19] Available at: https://urn.nsk.hr/urn:nbn:hr:195:107422

M. Pobar and I. Ipšić, "Online speaker de-identification using voice transformation", BiForD - Biometrics & Forensics & De-identification and Privacy Protection IEEE, 2014. [Online] Available at: https://urn.nsk.hr/urn:nbn:hr:195:107422 [Accessed: 19 December 2024]

Please login to the repository to save this object to your list.
Metadata
Title (english)Online speaker de-identification using voice transformation
AuthorMiran Pobar
AuthorIvo Ipšić
Author's institutionUniversity of Rijeka
(Faculty of Informatics and Digital Technologies)
Scientific / art field,
discipline and subdiscipline		SOCIAL SCIENCES
Information and Communication Sciences
Scientific / art field,
discipline and subdiscipline		TECHNICAL SCIENCES
Computing
Abstract (english)
Speaker de-identification is the process by which speech is transformed in a way that the speaker identity is masked, while at the same time the transformed speech preserves acoustic information that contributes to the intelligibility, naturalness and clarity. Systems that perform speech de-identification could be used in voice driven applications (for example in call centres) where the speaker's identity has to be hidden. The paper describes the experiments we have performed in order to de-identify speech using GMM based voice transformation techniques and speaker identification using freely available tools. We propose a method by which speakers whose speech has not been used to build voice transformations (for training) can be efficiently de-identified online. The proposed method is evaluated using a speech database of read speech and a small set of speakers. The results we present show that the proposed de-identification method performs similarly as a closed-set de-identification procedure that requires previous enrolment and can efficiently be used for online speaker de-identification.
Keywords (english)
Languageenglish
Publication typeScientific paper - Original scientific paper
Publication statusPublished
Peer reviewPeer review - international
Publication versionAccepted version
Publication titleBiForD - Biometrics & Forensics & De-identification and Privacy Protection
Numberingpp. 39-41
ISBN978-953-233-079-3
DOIhttps://doi.org/10.1109/MIPRO.2014.6859761
URN:NBNurn:nbn:hr:195:107422
Publication2014-06-24
ProjectNumber: 318-0361935-0852
Title (croatian): Govorne tehnologije
Title (english): Speech Technologies
Leader: Ivo Ipšić
Jurisdiction: Croatia
Funding stream: ZP
ConferenceTitle: 2014 37th International Convention on Information and Communication Technology, Electronics and Microelectronics (MIPRO)
Acronym: MIPRO 2014
Location: Opatija, Croatia
Organizer: Hrvatska udruga za informacijsku i komunikacijsku tehnologiju, elektroniku i mikroelektroniku - MIPRO
Start date: 2014-05-26
End date: 2014-05-30
Assembly type: Lecture
Document URLhttps://ieeexplore.ieee.org/abstract/document/6859761
Type of resourceText
PublisherIEEE
Access conditionsOpen access
Terms of useLicence In copyright icon
Public note© 2014 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.
Created on2023-08-03 08:43:27