Naslov
Online speaker de-identification using voice transformation

Autori
Pobar, Miran ; Ipšić, Ivo

Vrsta, podvrsta i kategorija rada
Radovi u zbornicima skupova, cjeloviti rad (in extenso), znanstveni

Izvornik
BiForD - Biometrics & Forensics & De-identification and Privacy Protection / Ribarić, Slobodan - Rijeka : Hrvatska udruga za informacijsku i komunikacijsku tehnologiju, elektroniku i mikroelektroniku - MIPRO, 2014, 39-42

ISBN
978-953-233-079-3

Skup
37th International Convention on Information and Communication Technology, Electronics and Microelectronics (MIPRO), 2014

Mjesto i datum
Opatija, Hrvatska, 26.05.2014. - 30.05.2014

Vrsta sudjelovanja
Predavanje

Vrsta recenzije
Međunarodna recenzija

Ključne riječi
speaker de-identification; voice transformation; online de-identification

Sažetak
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, natur- alness 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 pro- cedure that requires previous enrolment and can efficiently be used for online speaker de- identification.

Izvorni jezik
Engleski

Znanstvena područja
Računarstvo, Informacijske i komunikacijske znanosti

POVEZANOST RADA