Voice disguise by mimicry: deriving statistical articulometric evidence to evaluate claimed impersonation

  title={Voice disguise by mimicry: deriving statistical articulometric evidence to evaluate claimed impersonation},
  author={Rita Singh and Abelino Jim{\'e}nez and Anders {\O}land},
  journal={IET Biom.},
Voice disguise by impersonation is often used in voice-based crimes by perpetrators who try to evade identification while sounding genuine. Voice evidence from these crimes is analysed to both detect impersonation, and match the impersonated voice to the natural voice of the speaker to prove its correct ownership. There are interesting situations, however, where a speaker might be confronted with voice evidence that perceptually sounds like their natural voice but may deny ownership of it… 

Figures and Tables from this paper

Who owns your voice? Linguistic and legal perspectives on the relationship between vocal distinctiveness and the rights of the individual speaker

Only in very recent times has the concept of ‘ownership’ of a human voice begun to demand proper consideration in terms of its legal implications. The current lack of clarity with respect to the

Evaluation of Voice Mimicking Using I-Vector Framework

The fusion of mel-frequency cepstral coefficient-based i-vectors and phonation-based features is utilized to identify the most competent imitator who imitates a target voice in the proposed work.

A survey on presentation attack detection for automatic speaker verification systems: State-of-the-art, taxonomy, issues and future direction

A systematic analysis of the state-of-the-art voice PAD systems to promote further advancement in this area and to identify areas that require additional research.

Speaker Identity Tracing Using Fingerprint Data Hiding against Telecommunications Fraud

  • Hongxia WangJing Sang
  • Computer Science
    2018 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)
  • 2018
Experimental results show the proposed scheme can accurately trace the speaker identity in the remote speech communications, and prevent telecommunication fraud to some extent.

Applied Profiling: Uses, Reliability and Ethics

  • Rita Singh
  • Political Science
    Profiling Humans from their Voice
  • 2019
There are many uses of profiling, but there is a dichotomy associated with this progression: its increasing accuracy is likely to give rise to more applications, but its potential to severely infringe on a person's privacy through them will also rise.

A Corrective Learning Approach for Text-Independent Speaker Verification

Deep corrective learning networks (CLNets) are proposed that explicitly learn a mapping from a new speech segment and the current predictions, to a correction, to ensure that the predictions eventually converge to the ground truth after several corrections.



Formant manipulations in voice disguise by mimicry

The study of voice impersonations performed by an expert mimic is studied, focusing specifically on formants and formant-related measurements, to find out the extent and type of formant manipulations that are performed by the expert at the level of individual phonemes.

The imitated voice - a problem for voice line-ups?

This paper investigates whether imitation can pose a problem for speaker discrimination within the line-up. The voice chosen for the experiment was that of a well-known Swedish politician. A

Acoustic analysis of imitated voice produced by a professional impersonator

Comparisons of a voice produced by a professional impersonator imitating a target speaker and imitated voices demonstrate that the impersonator controls vocal tract acoustic characteristics as well as those of the glottal source and pitch frequency to imitate the target voice.

I-vectors meet imitators: on vulnerability of speaker verification systems against voice mimicry

This work studies the vulnerability of two well-known speaker recognition systems, traditional Gaussian mixture model – universal background model (GMM-UBM) and a state-of-the-art i-vector classifier with cosine scoring, which consists of one professional Finnish imitator impersonating five wellknown Finnish public figures.

How flexible is the human voice? - a case study of mimicry

A professional impersonation artist imitated three well-known Swedish public figures and it was found that he was able to mimic global speech rate very closely, but timing at the segmental level showed little or no change in the direction of the targets.

Can a Professional Imitator Fool a GMM-Based Speaker Verification System?

Assessment of empirically how a state-of-the-art text-independent speaker verification system behaves when confronted to imposting attempts from a professional imitator shows that the knowledge of the lexical content of the access significantly helps the imitators, although fortunately not enough to fool the system.

The social life of voices: studying the neural bases for the expression and perception of the self and others during spoken communication

In 2013, London Underground reinstated the actor Oswald Laurence's famous “Mind the gap” announcement at Embankment station, having learned that the widow of the actor had been regularly visiting

Vulnerability of speaker verification systems against voice conversion spoofing attacks: The case of telephone speech

Experiments on a subset of NIST 2006 SRE corpus indicate that the JFA method is most resilient against conversion attacks, but even it experiences more than 5-fold increase in the false acceptance rate.

T'ain't What You Say, It's the Way That You Say It—Left Insula and Inferior Frontal Cortex Work in Interaction with Superior Temporal Regions to Control the Performance of Vocal Impersonations

It is revealed that deliberate modulation of vocal identity recruits the left anterior insula and inferior frontal gyrus, supporting the planning of novel articulations, and bilateral sites in posterior superior temporal/inferior parietal cortex and a region in right middle/anterior STS showed greater responses.

Short-term analysis for estimating physical parameters of speakers

The findings show that the higher-resolution analysis does provide benefits over conventional analysis for estimating speaker height, although it is less useful in predicting age, and is tested on the prediction of heights and ages of speakers from a standard speech database.