Time-Contrastive Learning Based Deep Bottleneck Features for Text-Dependent Speaker Verification

Abstract

There are a number of studies about extraction of bottleneck (BN) features from deep neural networks (DNNs)trained to discriminate speakers, pass-phrases and triphone states for improving the performance of text-dependent speaker verification (TD-SV). However, a moderate success has been achieved. A recent study [1] presented a time contrastive learning (TCL) concept to explore the non-stationarity of brain signals for classification of brain states. Speech signals have similar non-stationarity property, and TCL further has the advantage of having no need for labeled data. We therefore present a TCL based BN feature extraction method. The method uniformly partitions each speech utterance in a training dataset into a predefined number of multi-frame segments. Each segment in an utterance corresponds to one class, and class labels are shared across utterances. DNNs are then trained to discriminate all speech frames among the classes to exploit the temporal structure of speech. In addition, we propose a segment-based unsupervised clustering algorithm to re-assign class labels to the segments. TD-SV experiments were conducted on the RedDots challenge database. The TCL-DNNs were trained using speech data of fixed pass-phrases that were excluded from the TD-SV evaluation set, so the learned features can be considered phrase-independent. We compare the performance of the proposed TCL bottleneck (BN) feature with those of short-time cepstral features and BN features extracted from DNNs discriminating speakers, pass-phrases, speaker+pass-phrase, as well as monophones whose labels and boundaries are generated by three different automatic speech recognition (ASR) systems. Experimental results show that the proposed TCL-BN outperforms cepstral features and speaker+pass-phrase discriminant BN features, and its performance is on par with those of ASR derived BN features. Moreover,....

Copyright (c) 2019 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works

References in corpus (7)

• Auto-Encoding Variational Bayes
• Conditional Generative Adversarial Networks for Speech Enhancement and Noise-Robust Speaker Verification
• Unsupervised Learning of Disentangled and Interpretable Representations from Sequential Data
• Time-Contrastive Learning Based Deep Bottleneck Features for Text-Dependent Speaker Verification
• Unsupervised Feature Learning from Temporal Data
• End-to-End Neural Segmental Models for Speech Recognition
• Sequence Prediction with Neural Segmental Models

Cited by in corpus (8)

• Nearest Neighbor-Based Contrastive Learning for Hyperspectral and LiDAR Data Classification
• Time-Contrastive Learning Based Deep Bottleneck Features for Text-Dependent Speaker Verification
• Vocal Tract Length Perturbation for Text-Dependent Speaker Verification with Autoregressive Prediction Coding
• On Bottleneck Features for Text-Dependent Speaker Verification Using X-vectors
• UIAI System for Short-Duration Speaker Verification Challenge 2020
• Data augmentation enhanced speaker enrollment for text-dependent speaker verification
• Data Generation Using Pass-phrase-dependent Deep Auto-encoders for Text-Dependent Speaker Verification
• Masked Autoencoders with Multi-Window Local-Global Attention Are Better Audio Learners