Statistical Models in Forensic Voice Comparison

@article{Morrison2020StatisticalMI,
  title={Statistical Models in Forensic Voice Comparison},
  author={G. Morrison and Ewald Enzinger and Daniel Ramos and Joaqu'in Gonz'alez-Rodr'iguez and Alicia Lozano-D'iez},
  journal={arXiv: Applications},
  year={2020},
  pages={451-497}
}
This chapter describes a number of signal-processing and statistical-modeling techniques that are commonly used to calculate likelihood ratios in human-supervised automatic approaches to forensic voice comparison. Techniques described include mel-frequency cepstral coefficients (MFCCs) feature extraction, Gaussian mixture model - universal background model (GMM-UBM) systems, i-vector - probabilistic linear discriminant analysis (i-vector PLDA) systems, deep neural network (DNN) based systems… Expand
1 Citations

References

SHOWING 1-10 OF 124 REFERENCES
Voice source features for forensic voice comparison - an evaluation of the GLOTTEX software package
  • 6
  • PDF
Analysis of DNN approaches to speaker identification
  • 94
  • Highly Influential
  • PDF
The impact in forensic voice comparison of lack of calibration and of mismatched conditions between the known-speaker recording and the relevant-population sample recordings.
  • G. Morrison
  • Computer Science, Medicine
  • Forensic science international
  • 2018
  • 6
  • PDF
Reliability of voice comparison for forensic applications
  • 3
  • Highly Influential
Bayesian Speaker Verification with Heavy-Tailed Priors
  • 693
  • PDF
Forensic speech science
  • 20
A novel scheme for speaker recognition using a phonetically-aware deep neural network
  • 521
  • PDF
Insights into deep neural networks for speaker recognition
  • 43
  • PDF
...
1
2
3
4
5
...