CBC-Based Synthetic Speech Detection

CBC-Based Synthetic Speech Detection

Jichen Yang (School of Electronic and Information Engineering, South China University of Technology, Guangzhou, China), Qianhua He (School of Electronic and Information Engineering, South China University of Technology, Guangzhou, China), Yongjian Hu (School of Electronic and Information Engineering, South China University of Technology, Guangzhou, China) and Weiqiang Pan (Information and Network Engineering and Research Centre, South China University of Technology, Guangzhou, China)
Copyright: © 2019 |Pages: 12
DOI: 10.4018/IJDCF.2019040105

Abstract

In previous studies of synthetic speech detection (SSD), the most widely used features are based on a linear power spectrum. Different from conventional methods, this article proposes a new feature extraction method for SSD from octave power spectrum which is obtained from constant-Q transform (CQT). By combining CQT, block transform (BT) and discrete cosine transform (DCT), a new feature is obtained, namely, constant-Q block coefficients (CBC). In which, CQT is used to transform speech from the time domain into the frequency domain, BT is used to segment octave power spectrum into many blocks and DCT is used to extract principal information of every block. The experimental results on ASVspoof 2015 corpus shows that CBC is superior to other front-ends features that have been benchmarked on ASVspoof 2015 evaluation set in terms of equal error rate (EER).
Article Preview
Top

Introduction

Automatic speaker verification (ASV) is the task to accept or reject an identity claim based on a person's speech sample (Kinnunen & Li, 2008), which has received wide spread attention over the recent 30 years. Most ASV systems assume natural human speech as input. However, ASV systems are often attacked by synthetic speech (Wu, et al, 2016), which is usually obtained by speech synthesis (SS) and voice conversation (VC) (Wu & Li, 2014). In order to protect ASV systems safe, it is necessary to detect synthetic speech from input speech. In addition, in the field of criminal investigators for forensics, SSD is helpful.

Generally speaking, there are two types of countermeasures for SSD: front-end feature and back-end model.

In terms of feature, features based on power spectrum, combining magnitude with phase and so on. The most widely used features based on power spectrum in SSD are mel-frequency cepstral coefficients (MFCC) (Sahidullah, Kinnunen & Hanilci, 2015) and constant-Q cepstral coefficients (CQCC) (Todisco, Delgado & Evans, 2016). In 2017, Paul et al. proposed several types of transformation for SSD in (Paul, Pal & Saha, 2017), they are speech-signal frequency cepstral coefficients (SFCC), mel-warped overlapped block transformation (MOBT), speech-signal-based overlapped block transformation (SOBT), inverted speech-signal frequency cepstral coefficients (ISFCC), inverted mel-warped overlapped block transformation (IMOBT). In addition, inverted mel frequency cepstral coefficients (IMFCC) (Chakroborty, Roy & Saha, 2007) is also used in (Sahidullah, Kinnunen & Hanilci, 2015). However, those features are all based on linear power spectrum that every frequency bin has the same frequency region.

Phase features were often combined with magnitude features in SSD because the performance of phase features is usually worse than commonly used features based on power spectrum. For example, In 2015, Xiao et al. used logarithm magnitude spectrum (LMS) + residual logarithm magnitude spectrum (RLMS) + group delay (GD) + modified group delay (MGD) + instantaneous frequency (IF) + baseband phase difference (BPD) + pitch synchronous phase (PSP) in (Xiao, Tian, Du, et al, 2015), Novoselov et al. used modified group delay cepstral coefficients (MGDCC) + MFCC + Mel-frequency principal coefficients (MFPC) in (Novoselov, Kozlov, et al, 2016).

In addition, there are some other features used in SSD. For example, Zhang et al. employed Teager energy operator critical band autocorrelation envelope plus perceptual minimum variance distortionless response (TCAEP) and spectrogram in SSD (Zhang, Ranjan, Nandwana, et al, 2016, Zhang,Yu, & Hansen, 2017). Sriskandaraja et al. proposed scattering cepstal coefficients (SCC) (Sriskandaraja, Sethu, Ambikairajah & Li, 2017) in SSD, respectively. Patel and Patil proposed to use fundamental frequency, strength of excitation and cochlear filter cepatral coefficients and instantaneous frequency (CFCC-IF) (Patel & Patil, 2015, Patel & Patil, 2016) in SSD. In (Sahidullah, Kinnunen & Hanilci, 2015), a series of features were compared in SSD by Md Sahidullah et al. They are rectangular filter cepstral coefficients (RFCC) (Hasen, Sadjadi, Liu, Shokouhi, Boril, & Hansen, 2013), linear frequency cepstral coefficients (LFCC) (Alegre, Amehraye, & Evans, 2013), linear prediction cepstral coefficients (LPCC) (Furui, 1981), perception linear prediction cepstral coefficients (PLPCC) (Hermansky, 1990), subband spectral fux coefficients (SSFC) (Scheirer & Slaney, 1997), spectral centroid magnitude coefficients (SCMC) (Kua, Thiruvaran, Nosratighods, Ambikairajah, Epps, 2010), subband centroid frequency coefficients (SCFC) (Kua, Thiruvaran, Nosratighods, Ambikairajah, Epps, 2010).

Complete Article List

Search this Journal:
Reset
Open Access Articles: Forthcoming
Volume 12: 4 Issues (2020): 1 Released, 3 Forthcoming
Volume 11: 4 Issues (2019)
Volume 10: 4 Issues (2018)
Volume 9: 4 Issues (2017)
Volume 8: 4 Issues (2016)
Volume 7: 4 Issues (2015)
Volume 6: 4 Issues (2014)
Volume 5: 4 Issues (2013)
Volume 4: 4 Issues (2012)
Volume 3: 4 Issues (2011)
Volume 2: 4 Issues (2010)
Volume 1: 4 Issues (2009)
View Complete Journal Contents Listing