Deep Neural Network Based Forensic Automatic Speaker Recognition in VOCALISE using x-Vectors

Kelly F, Forth O, Kent S, Gerlach L, Alexander A. Deep Neural Network Based Forensic Automatic Speaker Recognition in VOCALISE using x-Vectors. In: AES Conference: 2019 AES International Conference on Audio Forensics. Audio Engineering Society; 2019. Paper 27. Available from: https://aes.org/publications/elibrary-page/?id=20477

@inproceedings{Kelly2019_20477,
  author = {Kelly, Finnian and Forth, Oscar and Kent, Samuel and Gerlach, Linda and Alexander, Anil},
  title = {{Deep Neural Network Based Forensic Automatic Speaker Recognition in VOCALISE using x-Vectors}},
  booktitle = {AES Conference: 2019 AES International Conference on Audio Forensics},
  note = {Paper 27},
  year = {2019},
  month = jun,
  publisher = {Audio Engineering Society},
  url = {https://aes.org/publications/elibrary-page/?id=20477}
}

TY  - CPAPER
TI  - Deep Neural Network Based Forensic Automatic Speaker Recognition in VOCALISE using x-Vectors
AU  - Kelly, Finnian
AU  - Forth, Oscar
AU  - Kent, Samuel
AU  - Gerlach, Linda
AU  - Alexander, Anil
T2  - AES Conference: 2019 AES International Conference on Audio Forensics
M1  - Paper 27
PY  - 2019
DA  - 2019/06/06
UR  - https://aes.org/publications/elibrary-page/?id=20477
PB  - Audio Engineering Society
LA  - en
AB  - In this article we present a Deep Neural Network (DNN)-based version of the VOCALISE (Voice Comparison and Analysis of the Likelihood of Speech Evidence) forensic automatic speaker recognition system. DNNs mark a new phase in the evolution of automatic speaker recognition technology, providing a powerful framework for extracting highly-discriminative speaker-specific features from a recording of speech. The latest version of VOCALISE aims to preserve the ‘open-box’ philosophy of its predecessors, offering the forensic practitioner flexibility in the configuration and training of all parts of the automatic speaker recognition pipeline. VOCALISE continues to support both legacy and state-of-the-art speaker modelling algorithms, the latest of which is a DNN-based ‘x-vector’ framework, a state-of-the-art approach that leverages a DNN to extract compact speaker representations. Here, we introduce the x-vector framework and its implementation in VOCALISE, and demonstrate its powerful performance capabilities on some forensically relevant data.
ER  -