Effect of multi-condition training and speech enhancement methods on spoofing detection
- 1 July 2016
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-5
Abstract
Many researchers have demonstrated the good performance of spoofing detection systems under clean training and testing conditions. However, it is well known that the performance of speaker and speech recognition systems significantly degrades in noisy conditions. Therefore, it is of great interest to investigate the effect of noise on the performance of spoofing detection systems. In this paper, we investigate a multi-conditional training method where spoofing detection models are trained with a mix of clean and noisy data. In addition, we study the effect of different noise types as well as speech enhancement methods on a state-of-the-art spoofing detection system based on the dynamic linear frequency cepstral coefficients (LFCC) feature and a Gaussian mixture model maximum-likelihood (GMM-ML) classifier. In the experiment part we consider three additive noise types, Cantine, Babble and white Gaussian at different signal-to-noise ratios, and two mainstream speech enhancement methods, Wiener filtering and minimum mean-square error. The experimental results show that enhancement methods are not suitable for the spoofing detection task, as the spoofing detection accuracy will be reduced after speech enhancement. Multi-conditional training, however, shows potential at reducing error rates for spoofing detection.Keywords
This publication has 25 references indexed in Scilit:
- Librispeech: An ASR corpus based on public domain audio books2015
- Joint Speaker Verification and Antispoofing in the $i$ -Vector SpaceIEEE Transactions on Information Forensics and Security, 2015
- Toward a Universal Synthetic Speech Spoofing Detection Using Phase InformationIEEE Transactions on Information Forensics and Security, 2015
- Minimum Mean-Square Error Estimation of Mel-Frequency Cepstral Features–A Theoretically Consistent ApproachIEEE/ACM Transactions on Audio, Speech, and Language Processing, 2015
- Ideal ratio mask estimation using deep neural networks for robust speech recognition2013
- Statistical parametric speech synthesis using deep neural networks2013
- Speech enhancement based on a priori signal to noise estimation2002
- Multi-channel speech enhancement in a car environment using Wiener filtering and spectral subtraction2002
- Unit selection in a concatenative speech synthesis system using a large speech database1996
- Speech enhancement using a minimum mean-square error log-spectral amplitude estimatorIEEE Transactions on Acoustics, Speech, and Signal Processing, 1985