Investigation of spectral centroid features for cognitive load classification

Le, Phu Ngoc; Ambikairajah, Eliathamby; Epps, Julien; Sethu, Vidhyasaharan; Choi, Eric H. C.

doi:10.1016/j.specom.2011.01.005

Cited by 66 publications

(41 citation statements)

References 30 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…These features are computed from a power spectrum (power of magnitude of 512-sized fast Fourier transform) by applying one of the above filters of a given size (we use size 20 as per [15]). Spectral flux-based features, i.e., subband spectral flux coefficients (SSFC) [32], which are Euclidean distances between power spectrums (normalized by the maximum value) of two consecutive frames, subband centroid frequency (SCFC) [33], and subband centroid magnitude (SCMC) [33] coefficients are considered as well. A discrete cosine transform (DCT-II) is applied to these above features, except for SCFC, and first 20 coefficients are taken.…”

Section: Pads Failing To Generalizementioning

confidence: 99%

Presentation attack detection in voice biometrics

Korshunov¹,

Marcel²

2017

User-Centric Privacy and Security in Biometrics

View full text Add to dashboard Cite

Recent years have shown an increase in both the accuracy of biometric systems and their practical use. The application of biometrics is becoming widespread with fingerprint sensors in smartphones, automatic face recognition in social networks and video-based applications, and speaker recognition in phone banking and other phone-based services. The popularization of the biometric systems, however, exposed their major flaw -high vulnerability to spoofing attacks [1]. A fingerprint sensor can be easily tricked with a simple glue-made mold, a face recognition system can be accessed using a printed photo, and a speaker recognition system can be spoofed with a replay of pre-recorded voice. The ease with which a biometric system can be spoofed demonstrates the importance of developing efficient anti-spoofing systems that can detect both known (conceivable now) and unknown (possible in the future) spoofing attacks.Therefore, it is important to develop mechanisms that can detect such attacks, and it is equally important for these mechanisms to be seamlessly integrated into existing biometric systems for practical and attack-resistant solutions. To be practical, however, an attack detection should have (i) high accuracy, (ii) be well-generalized for different attacks, and (iii) be simple and efficient.One reason for the increasing demand for effective presentation attack detection (PAD) systems is the ease of access to people's biometric data. So often, a potential attacker can almost effortlessly obtain necessary biometric samples from social networks, including facial images, audio and video recordings, and even extract fingerprints from high resolution images. Therefore, various privacy protection solutions, such as legal privacy requirements and algorithms for obfuscating personal information, e.g., visual privacy filters [2], as well as, social awareness of threats to privacy can also increase security of personal information and potentially reduce the vulnerability of biometric systems.In this chapter, however, we focus on presentation attacks detection in voice biometrics, i.e., automatic speaker verification (ASV) systems. We discuss vulnerabilities of these systems to presentation attacks (PAs), present different state of the art 1

show abstract

Section: Pads Failing To Generalizementioning

confidence: 99%

Presentation attack detection in voice biometrics

Korshunov¹,

Marcel²

2017

User-Centric Privacy and Security in Biometrics

View full text Add to dashboard Cite

show abstract

“…Yap et al (2011a) also used score-level fusion of the CPP-based classification with the formant frequency-based system and yielded a final improved accuracy of 62.7% in cognitive load classification. Le et al (2011) investigated the use of speech's spectral centroid frequency (SCF) and spectral centroid amplitude (SCA) features for automatic cognitive load measurement. They found that the spectral centroid features consistently and significantly outperform a baseline system employing MFCC, pitch, and intensity features.…”

Section: Speech Signal Based Measuresmentioning

confidence: 99%

Robust Multimodal Cognitive Load Measurement (RMCLM)

Chen¹

2013

View full text Add to dashboard Cite

This report summarizes the important research activities, study results and research accomplishments out of the RMCLM project in the past year period. The objective of this project includes research of the fundamental issues related to the use of multiple input modalities and their fusion to enable robust and automatic cognitive load measurement (CLM) in the real world. Firstly, we carried out a further literature review on physiological measures of cognitive workload to include the recent advances of physiological measures of cognitive workload. In the meantime, we examined the use of various features (e.g. spectral and approximate entropies, wavelet-based complexity measures, correlation dimension, Hurst exponent) of electroencephalogram (EEG) signals to evaluate changes in working memory load during the performance of a cognitive task with varying difficulty/load levels. Eye based CLM was also studied. Three types of eye activity were investigated: pupillary response, blink, and eye movement (fixation and saccade). We further investigated the linguistic feature based CLM in this study and analyzed novel linguistic features as potential indices of cognitive load. All together, we had carried out CLM study of three unobtrusive modalities, namely EEG, eye activity, and linguistic feature based CLM, in the past year period. List of Publications Report Documentation PageForm Approved OMB No. Public reporting burden for the collection of information is estimated to average 1 hour per response, including the time for reviewing instructions, searching existing data sources, gathering and maintaining the data needed, and completing and reviewing the collection of information. Send comments regarding this burden estimate or any other aspect of this collection of information, including suggestions for reducing this burden, to Washington Headquarters Services, Directorate for Information Operations and Reports, 1215 Jefferson Davis Highway, Suite 1204, Arlington VA 22202-4302. Respondents should be aware that notwithstanding any other provision of law, no person shall be subject to a penalty for failing to comply with a collection of information if it does not display a currently valid OMB control number. REPORT DATE APR 20132. REPORT TYPE This report summarizes the important research activities, study results and research accomplishments out of the RMCLM project in the past year period. The objective of this project includes research of the fundamental issues related to the use of multiple input modalities and their fusion to enable robust and automatic cognitive load measurement (CLM) in the real world. Firstly, we carried out a further literature review on physiological measures of cognitive workload to include the recent advances of physiological measures of cognitive workload. In the meantime, we examined the use of various features (e.g. spectral and approximate entropies, wavelet-based complexity measures, correlation dimension, Hurst exponent) of electroencephalogram (EEG) signals to evaluate changes ...

show abstract

“…Hence, we have implemented: GMM-based classifier using cepstralbased features with rectangular (RFCC), mel-scale triangular (MFCC) [10], inverted mel-scale triangular (IMFCC), and linear triangular (LFCC) filters [11], spectral flux-based features (SSFC) [12], subband centroid frequency (SCFC) [13], and subband centroid magnitude (SCMC) [13] features. We also included recently proposed constant Q cepstral coefficients (CQCCs) [14], which were shown good performance on ASVspoof database 4 .…”

Section: Introductionmentioning

confidence: 99%

Impact of Score Fusion on Voice Biometrics and Presentation Attack Detection in Cross-Database Evaluations

Korshunov

Marcel

2017

IEEE J. Sel. Top. Signal Process.

View full text Add to dashboard Cite

Abstract-Research in the area of automatic speaker verification (ASV) has advanced enough for the industry to start using ASV systems in practical applications. However, these systems are highly vulnerable to spoofing or presentation attacks, limiting their wide deployment. Therefore, it is important to develop mechanisms that can detect such attacks, and it is equally important for these mechanisms to be seamlessly integrated into existing ASV systems for practical and attack-resistant solutions. To be practical, however, an attack detection should have (i) high accuracy, (ii) be well-generalized for different attacks, and (iii) be simple and efficient. Several audio-based presentation attack detection (PAD) methods have been proposed recently but their evaluation was usually done on a single, often obscure, database with limited number of attacks. Therefore, in this paper, we conduct an extensive study of eight state of the art PAD methods and evaluate their ability to detect known and unknown attacks (e.g., in a cross-database scenario) using two major publicly available speaker databases with spoofing attacks: AVspoof and ASVspoof. We investigate whether combining several PAD systems via score fusion can improve attack detection accuracy. We also study the impact of fusing PAD systems (via parallel and cascading schemes) with two i-vector and inter-session variability (ISV)-based ASV systems on the overall performance in both bona fide (no attacks) and spoof scenarios. The evaluation results question the efficiency and practicality of the existing PAD systems, especially when comparing results for individual databases and cross-database data. Fusing several PAD systems can lead to a slightly improved performance, however, how to select which systems to fuse remains an open question. Joint ASV-PAD systems show a significantly increased resistance to the attacks at the expense of slightly degraded performance for bona fide scenarios.

show abstract

Investigation of spectral centroid features for cognitive load classification

Cited by 66 publications

References 30 publications

Presentation attack detection in voice biometrics

Presentation attack detection in voice biometrics

Robust Multimodal Cognitive Load Measurement (RMCLM)

Impact of Score Fusion on Voice Biometrics and Presentation Attack Detection in Cross-Database Evaluations

Contact Info

Product

Resources

About