A Study of Intentional Voice Modifications for Evading Automatic Speaker Recognition

Kajarekar, Sachin; Bratt, Harry; Shriberg, Elizabeth; León, Romina De

doi:10.1109/odyssey.2006.248123

Cited by 30 publications

(17 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…[5] showed the harmonic part of the speech signal contains speaker dependent information that can be transformed to mimic another speaker. [6] studied the impact of intentional voice modifications performed by humans and showed that it makes both humans and speaker recognition systems vulnerable. A recent study in [7] investigated the effect of transformed speech on speaker recognition performance and showed that voice transformation can result in drastic increase of the false acceptance rate.…”

Section: Introductionmentioning

confidence: 99%

Voice convergin: Speaker de-identification by voice transformation

Qin

Toth

Schultz

et al. 2009

2009 IEEE International Conference on Acoustics, Speech and Signal Processing

View full text Add to dashboard Cite

Speaker identification might be a suitable answer to prevent unauthorized access to personal data. However we also need to provide solutions to secure transmission of spoken information. This challenge divides into two major aspects. First, the secure transmission of the content of the spoken input and second the secure transmission of the identity of the speaker. In this paper we concentrate on the latter, i.e. how to securely transmit information via voice without revealing the identity of the speaker to unauthorized listeners. In order to make the first steps toward solving this problem we study in this paper the potential of voice transformation for speaker de-identification. We use two speaker identification approaches to verify the success of de-identification with voice transformation, a GMM-based and a Phonetic approach, and study different voice transformation strategies to disguise speaker identity information while preserving understandability.

show abstract

Section: Introductionmentioning

confidence: 99%

Voice convergin: Speaker de-identification by voice transformation

Qin

Toth

Schultz

et al. 2009

2009 IEEE International Conference on Acoustics, Speech and Signal Processing

View full text Add to dashboard Cite

show abstract

“…Uncooperative speakers who would like to avoid being identified may try to intentionally fool a system by changing their speaking behavior or lowering their voices. Kajarekar et al investigated the effect of intentional voice modifications on the speaker recognition and showed vulnerability in both humans and speaker recognition systems to changed voices [8].…”

Section: Introductionmentioning

confidence: 99%

Whispering Speaker Identification

Qin

Jou

Schultz

2007

Multimedia and Expo, 2007 IEEE International Conference On

View full text Add to dashboard Cite

This paper describes a study of automatically identifying whispering speakers. People usually whisper in order to avoid being identified or overheard by lowering their voices. The study compares performances between normal and whispered speech mode in clean and noisy environment under matched and mismatched training conditions, and describes the impact of feature warping and throat microphone on noise reduction. Score combination strategies are used when only little whisper data is available to improve performance. In sum, we achieved 8% to 33% relative improvements in identification accuracy with only 5 to 10 seconds noisy whispered speech data per speaker.

show abstract

“…A significant degradation was shown only when the reference population was assembled with normal speech, and highly mitigated when testing over reference populations containing the same type of disguise, which suggests a lack of robustness of this spectral-based system when dealing with such voice disguises. In the same line, [Kajarekar et al 2006] analysed the effect of intentional voice modifications regarding speaking style -which turned out to be reflected by means of modifying pitch, duration or mimicking an accent by most of the speakers-against a GMM-based speaker recognition system using 13 MFCC on the FISHER database, as a part of the NIST 2003 Extended Speaker Recognition Evaluation (SRE 1 ). The results showed an increase of the EER from 0.05% -tested with normal voices-to 7.46% -tested with disguised voices-, representing a 39% of false rejection of subjects disguising their voices.…”

Section: Voice Imitation and Modificationmentioning

confidence: 99%

Voice Disguise in Automatic Speaker Recognition

Farrús

2018

ACM Comput. Surv.

View full text Add to dashboard Cite

We, humans, are able to identify other people even in voice disguise conditions. However, we are not immune to all voice changes when trying to identifying people from voice. Likewise, automatic speaker recognition systems can also be deceived by voice imitation and other types of disguise. Taking into account the voice disguise classification into the combination of two different categories (deliberate/non-deliberate and electronic/non-electronic), this survey provides a literature review on the influence of voice disguise in the automatic speaker recognition task and the robustness of these systems to such voice changes. Additionally, the survey addresses existing applications dealing with voice disguise and analyses some issues for future research.

show abstract

A Study of Intentional Voice Modifications for Evading Automatic Speaker Recognition

Cited by 30 publications

References 8 publications

Voice convergin: Speaker de-identification by voice transformation

Voice convergin: Speaker de-identification by voice transformation

Whispering Speaker Identification

Voice Disguise in Automatic Speaker Recognition

Contact Info

Product

Resources

About