Cochlear Filter and Instantaneous Frequency Based Features for Spoofed Speech Detection

Patel, Tanvina B.; Patil, Hemant A.

doi:10.1109/jstsp.2016.2647201

Cited by 35 publications

(13 citation statements)

References 35 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This might propose that front-end side should be focused more for countermeasures of spoofing than on the sophisticated classifiers. This view is supported by the results of the recent ASV Spoof 2015 Challenge, during INTERSPEECH 2015 [1]- [2].…”

Section: Introductionmentioning

confidence: 67%

Novel energy separation based instantaneous frequency features for spoof speech detection

Kamble

Patil

2017

2017 25th European Signal Processing Conference (EUSIPCO)

Self Cite

View full text Add to dashboard Cite

Abstract-Speech Synthesis (SS) and Voice Conversion (VC) presents a genuine risk of attacks for Automatic Speaker Verification (ASV) technology. In this paper, we evaluate front-end anti-spoofing technique to protect ASV system for SS and VC attack using a standard benchmarking database. In particular, we propose a novel feature set, namely, Energy Separation Algorithm-based Instantaneous Frequency Cosine Coefficients (ESA-IFCC) to detect the genuine and impostor speech. The experiments are carried out on ASV Spoof 2015 Challenge database. On the development set, the score-level fusion of proposed ESA-IFCC feature set with Mel Frequency Cepstral Coefficients (MFCC) gave an EER of 3.45 %, which reduced significantly from MFCC (6.98 %) and ESA-IFCC (5.43 %) with 13-D static features. The EER decreases further to 2.01 % and 1.89 % for ∆ and ∆∆ features derived from proposed ESA-IFCC features, respectively. The overall average error rate for known and unknown attacks in evaluation set was 6.79 % for ESA-IFCC and was significantly better than the MFCC (9.15 %) features.

show abstract

Section: Introductionmentioning

confidence: 67%

Novel energy separation based instantaneous frequency features for spoof speech detection

Kamble

Patil

2017

2017 25th European Signal Processing Conference (EUSIPCO)

Self Cite

View full text Add to dashboard Cite

show abstract

“…The CFCCIF features were used by the authors in the first ASVspoof 2015 challenge that makes use of envelope of the output of each cochlear filter and its IF for spoof detection [39,42]. For the present task of replay detection both natural and replay speech is from the human speaker, hence, the derivative operation is eliminated from original CFCCIF method.…”

Section: Cochlear Filter Cepstral Coefficients and Instantaneous Freqmentioning

confidence: 99%

“…The decision of the test speech being genuine or replay is based on the LLR. To obtain the complementary information of CQCC, CFCCIF, Prosody, MFCC and VESA-IFCC features, we use their score-level fusion as in our other studies [41,42]. The performance is measured by computing the Equal Error Rate (EER) as in [17].…”

Section: Asv Spoof 2017 Database and Model Trainingmentioning

confidence: 99%

Novel Variable Length Teager Energy Separation Based Instantaneous Frequency Features for Replay Detection

Patil¹,

Kamble²,

Patel³

et al. 2017

Interspeech 2017

Self Cite

View full text Add to dashboard Cite

Replay attacks presents a great risk for Automatic Speaker Verification (ASV) system. In this paper, we propose a novel replay detector based on Variable length Teager Energy Operator-Energy Separation Algorithm-Instantaneous Frequency Cosine Coefficients (VESA-IFCC) for the ASV spoof 2017 challenge.The key idea here is to exploit the contribution of IF in each subband energy via ESA to capture possible changes in spectral envelope (due to transmission and channel characteristics of replay device) of replayed speech. The IF is computed from narrowband components of speech signal, and DCT is applied in IF to get proposed feature set. We compare the performance of the proposed VESA-IFCC feature set with the features developed for detecting synthetic and voice converted speech. This includes the CQCC, CFCCIF and prosody-based features. On the development set, the proposed VESA-IFCC features when fused at score-level with a variant of CFCCIF and prosodybased features gave the least EER of 0.12 %. On the evaluation set, this combination gave an EER of 18.33 %. However, post-evaluation results of challenge indicate that VESA-IFCC features alone gave the relatively least EER of 14.06 % (i.e., relatively 16.11 % less compared to baseline CQCC) and hence, is a very useful countermeasure to detect replay attacks.Variable length Teager Energy Operator (VTEO) is the modified version of the traditional TEO method [27]. TEO involves nonlinear operations on the signal, i.e, square of current sample and multiplication of previous and next sample, i.e., x(n − 1)

show abstract

“…The ASV-spoof-challenge was first proposed in 2015 to detect attacks based on speech synthesis, and voice conversion. Many spoof detection algorithms have been able to counter such attacks [5][6][7]. The replay attack is a process where the pre-recorded utterance of a genuine speaker is replayed by an impostor to access the ASV system.…”

Section: Introductionmentioning

confidence: 99%

Decision-level Feature Switching as a Paradigm for Replay Attack Detection

Saranya¹,

Murthy²

2018

Interspeech 2018

View full text Add to dashboard Cite

A pre-recorded audio sample of an authentic speaker presented to a voice-based biometric system is termed as a replay attack. Such attacks can be detected by identifying the characteristics of the recording device and environment. An analysis of different recording devices indicates that each recording device affects the spectrum differently. It is also observed that each feature captures specific characteristics of recording devices. In particular, Mel Filterbank Slope (MFS) captures low-frequency information corresponding to that of the low-quality recording devices, while Linear Filterbank Slope (LFS) captures highfrequency information which corresponds to that of a highquality recording device. The proposed approach uses MFS and LFS along with Mel Frequency Cepstral Coefficients (MFCC) and Constant-Q Cepstral Coefficients (CQCC) in a Decisionlevel Feature Switching (DLFS) paradigm to determine whether a given utterance is spoofed. The obtained results surpass the state-of-the-art Light Convolutional Neural Network (LCNN) based replay detection system with a relative improvement of 7.43% on the ASV-spoof-2017 evaluation dataset.

show abstract

Cochlear Filter and Instantaneous Frequency Based Features for Spoofed Speech Detection

Cited by 35 publications

References 35 publications

Novel energy separation based instantaneous frequency features for spoof speech detection

Novel energy separation based instantaneous frequency features for spoof speech detection

Novel Variable Length Teager Energy Separation Based Instantaneous Frequency Features for Replay Detection

Decision-level Feature Switching as a Paradigm for Replay Attack Detection

Contact Info

Product

Resources

About