End-to-end spoofing detection with raw waveform CLDNNs

TL;DR

This paper introduces a novel end-to-end deep learning model based on raw waveforms for spoofing detection in speaker verification, achieving state-of-the-art accuracy without pre- or post-processing.

Contribution

The paper presents a raw waveform CLDNN model that jointly extracts features and classifies speech signals, streamlining spoofing detection.

Findings

Significantly reduces half total error rate to 0.82% on BTAS2016 dataset

Performs well under unknown spoofing conditions

Outperforms previous methods with a simpler end-to-end approach

Abstract

Albeit recent progress in speaker verification generates powerful models, malicious attacks in the form of spoofed speech, are generally not coped with. Recent results in ASVSpoof2015 and BTAS2016 challenges indicate that spoof-aware features are a possible solution to this problem. Most successful methods in both challenges focus on spoof-aware features, rather than focusing on a powerful classifier. In this paper we present a novel raw waveform based deep model for spoofing detection, which jointly acts as a feature extractor and classifier, thus allowing it to directly classify speech signals. This approach can be considered as an end-to-end classifier, which removes the need for any pre- or post-processing on the data, making training and evaluation a streamlined process, consuming less time than other neural-network based approaches. The experiments on the BTAS2016 dataset show that the system performance is significantly improved by the proposed raw waveform convolutional long short term neural network (CLDNN), from the previous best published 1.26\% half total error rate (HTER) to the current 0.82\% HTER. Moreover it shows that the proposed system also performs well under the unknown (RE-PH2-PH3,RE-LPPH2-PH3) conditions.