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

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.

[1]  Daniel Garcia-Romero,et al.  Analysis of i-vector Length Normalization in Speaker Recognition Systems , 2011, INTERSPEECH.

[2]  Sadaoki Furui,et al.  Speaker-independent isolated word recognition using dynamic features of speech spectrum , 1986, IEEE Trans. Acoust. Speech Signal Process..

[3]  Andrzej Drygajlo,et al.  Methodological Guidelines for Best Practice in Forensic Semiautomatic and Automatic Speaker Recognition including Guidance on the Conduct of Proficiency Testing and Collaborative Exercises , 2016 .

[4]  Anil Alexander,et al.  Forensic Voice Comparisons in German with Phonetic and Automatic Features Using Vocalise Software , 2014 .

[5]  S. Furui,et al.  Cepstral analysis technique for automatic speaker verification , 1981 .

[6]  M. Picheny,et al.  Comparison of Parametric Representation for Monosyllabic Word Recognition in Continuously Spoken Sentences , 2017 .

[7]  Douglas A. Reynolds,et al.  Speaker Verification Using Adapted Gaussian Mixture Models , 2000, Digit. Signal Process..

[8]  G. McLachlan.  Discriminant Analysis and Statistical Pattern Recognition , 1992 .

[9]  Mitchell McLaren,et al.  How to train your speaker embeddings extractor , 2018, Odyssey.

[10]  Haizhou Li,et al.  An overview of text-independent speaker recognition: From features to supervectors , 2010, Speech Commun..

[11]  Finnian Kelly,et al.  VOCALISE : A forensic automatic speaker recognition system supporting spectral , phonetic , and user-provided features , 2016 .

[12]  Sanjeev Khudanpur,et al.  X-Vectors: Robust DNN Embeddings for Speaker Recognition , 2018, 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

[13]  Guigang Zhang,et al.  Deep Learning , 2016, Int. J. Semantic Comput..

[14]  John H. L. Hansen,et al.  Speaker Recognition by Machines and Humans: A tutorial review , 2015, IEEE Signal Processing Magazine.

[15]  Patrick Kenny,et al.  Front-End Factor Analysis for Speaker Verification , 2011, IEEE Transactions on Audio, Speech, and Language Processing.

[16]  Paul Boersma,et al.  Praat: doing phonetics by computer , 2003 .

[17]  James H. Elder,et al.  Probabilistic Linear Discriminant Analysis for Inferences About Identity , 2007, 2007 IEEE 11th International Conference on Computer Vision.