Gaussian-constrained Training for Speaker Verification

Neural models, in particular the d-vector and x-vector architectures, have produced state-of-the-art performance on many speaker verification tasks. However, two potential problems of these neural models deserve more investigation. Firstly, both models suffer from ‘information leak’, which means that some parameters participating in model training will be discarded during inference, i.e, the layers that are used as the classifier. Secondly, these models do not regulate the distribution of the derived speaker vectors. This ‘unconstrained distribution’ may degrade the performance of the subsequent scoring component, e.g., PLDA. This paper proposes a Gaussian-constrained training approach that (1) discards the parametric classifier, and (2) enforces the distribution of the derived speaker vectors to be Gaussian. Our experiments on the VoxCeleb and SITW databases demonstrated that this new training approach produced more representative and regular speaker embeddings, leading to consistent performance improvement.

[1]  Erik McDermott,et al.  Deep neural networks for small footprint text-dependent speaker verification , 2014, 2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

[2]  Patrick Kenny,et al.  Joint Factor Analysis Versus Eigenchannels in Speaker Recognition , 2007, IEEE Transactions on Audio, Speech, and Language Processing.

[3]  Daniel Povey,et al.  The Kaldi Speech Recognition Toolkit , 2011 .

[4]  Georg Heigold,et al.  End-to-end text-dependent speaker verification , 2015, 2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

[5]  Themos Stafylakis,et al.  Deep Neural Networks for extracting Baum-Welch statistics for Speaker Recognition , 2014, Odyssey.

[6]  Aaron Lawson,et al.  The Speakers in the Wild (SITW) Speaker Recognition Database , 2016, INTERSPEECH.

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

[8]  Florin Curelaru,et al.  Front-End Factor Analysis For Speaker Verification , 2018, 2018 International Conference on Communications (COMM).

[9]  Daniel Povey,et al.  MUSAN: A Music, Speech, and Noise Corpus , 2015, ArXiv.

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

[11]  Sergey Ioffe,et al.  Probabilistic Linear Discriminant Analysis , 2006, ECCV.

[12]  Yifan Gong,et al.  End-to-End attention based text-dependent speaker verification , 2016, 2016 IEEE Spoken Language Technology Workshop (SLT).

[13]  Dong Wang,et al.  Full-Info Training for Deep Speaker Feature Learning , 2018, 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

[14]  Sanjeev Khudanpur,et al.  A study on data augmentation of reverberant speech for robust speech recognition , 2017, 2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

[15]  Joon Son Chung,et al.  VoxCeleb: A Large-Scale Speaker Identification Dataset , 2017, INTERSPEECH.

[16]  Sanjeev Khudanpur,et al.  Deep Neural Network Embeddings for Text-Independent Speaker Verification , 2017, INTERSPEECH.

[17]  Sanjeev Khudanpur,et al.  Deep neural network-based speaker embeddings for end-to-end speaker verification , 2016, 2016 IEEE Spoken Language Technology Workshop (SLT).

[18]  Dong Wang,et al.  Deep Speaker Feature Learning for Text-Independent Speaker Verification , 2017, INTERSPEECH.

[19]  Yun Lei,et al.  A novel scheme for speaker recognition using a phonetically-aware deep neural network , 2014, 2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).