Visible to the public Acoustic Fingerprints 2015Conflict Detection Enabled

SoS Newsletter- Advanced Book Block


SoS Logo

Acoustic Fingerprints 2015

Acoustic fingerprints can be used to identify an audio sample or quickly locate similar items in an audio database. As a security tool, fingerprints offer a modality of biometric identification of a user. Current research is exploring various aspects and applications, including the use of these fingerprints for mobile device security, antiforensics, use of image processing techniques, and client side embedding.  The research work cited here was presented in 2015.

Tsai, T.J.; Friedland, G.; Anguera, X., "An Information-Theoretic Metric of Fingerprint Effectiveness," in Acoustics, Speech and Signal Processing (ICASSP), 2015 IEEE International Conference on, pp. 340-344, 19-24 April 2015. doi: 10.1109/ICASSP.2015.7177987

Abstract: Audio fingerprinting refers to the process of extracting a robust, compact representation of audio which can be used to uniquely identify an audio segment. Works in the audio fingerprinting literature generally report results using system-level metrics. Because these systems are usually very complex, the overall system-level performance depends on many different factors. So, while these metrics are useful in understanding how well the entire system performs, they are not very useful in knowing how good or bad the fingerprint design is. In this work, we propose a metric of fingerprint effectiveness that decouples the effect of other system components such as the search mechanism or the nature of the database. The metric is simple, easy to compute, and has a clear interpretation from an information theory perspective. We demonstrate that the metric correlates directly with system-level metrics in assessing fingerprint effectiveness, and we show how it can be used in practice to diagnose the weaknesses in a fingerprint design.

Keywords: audio coding; audio signal processing; copy protection; signal representation; audio fingerprinting literature; audio representation extraction; audio segment; fingerprint effectiveness; information theoretic metric; search mechanism; system level metrics; system level performance; Accuracy; Databases; Entropy; Information rates; Noise measurement; Signal to noise ratio; audio fingerprint; copy detection (ID#: 15-8805)



Szlosarczyk, Sebastian; Schulte, Andrea, "Voice Encrypted Recognition Authentication - VERA," in Next Generation Mobile Applications, Services and Technologies, 2015 9th International Conference on,  pp. 270-274, 9-11 Sept. 2015. doi: 10.1109/NGMAST.2015.74

Abstract: We propose VERA - an authentication scheme where sensitive data on mobile phones can be secured or whereby services can be locked by the user's voice. Our algorithm takes use of acoustic fingerprints to identify the personalized voice. The security of the algorithm depends on the discrete logarithm problem in ZN where N is a safe prime. Further we evaluate two practical examples on Android devices where our scheme is used: First the encryption of any data(set). Second locking a mobile phone. Voice is the basic for both of the fields.

Keywords: Acoustics; Authentication; Encryption; Mobile handsets; Protocols; Android; acoustic fingerprint; authentication; biometrics; cryptography; encryption; voice (ID#: 15-8806)



Casagranda, P.; Sapino, M.L.; Candan, K.S., "Audio Assisted Group Detection Using Smartphones," in Multimedia & Expo Workshops (ICMEW), 2015 IEEE International Conference on, pp. 1-6, June 29 2015-July 3 2015. doi: 10.1109/ICMEW.2015.7169764

Abstract: In this paper we introduce a novel technique to discover groups of users sharing the same environment: a room, an office, a car. Using a smartphone device, we propose a method based on the joint usage of GPS and acoustic fingerprints, allowing to greatly improve the precision of GPS only group detection. To reach the objective, we use a novel variation of an existing audio fingerprinting algorithm with good noise tolerance, assessing it under several conditions. The method is shown to be especially effective for groups of listeners of audio and audio visual content. We finally propose an application of the method to deliver content recommendations for a specific use case, hybrid content radio, an adaptive radio service discussed in the European Broadcasting Union, allowing the enrichment of traditional broadcast linear radio with personalized and context-aware audio content.

Keywords: Global Positioning System; audio signal processing; mobile computing; mobility management (mobile radio); object detection; radio broadcasting; smart phones; European Broadcasting Union; GPS; acoustic fingerprints; audio assisted group detection; audio fingerprinting algorithm; audio visual content; broadcast linear radio; content recommendations; context-aware audio content; hybrid content radio; noise tolerance; smartphone device; Global Positioning System; Audience discovery; audio fingerprinting; contextual recommendation; group detection; group recommendation; hybrid content radio (ID#: 15-8807)



Sankupellay, M.; Towsey, M.; Truskinger, A.; Roe, P., "Visual Fingerprints of the Acoustic Environment: The Use of Acoustic Indices to Characterise Natural Habitats," in Big Data Visual Analytics (BDVA), 2015, pp. 1-8, 22-25 Sept. 2015. doi: 10.1109/BDVA.2015.7314306

Abstract: Acoustic recordings play an increasingly important role in monitoring terrestrial environments. However, due to rapid advances in technology, ecologists are accumulating more audio than they can listen to. Our approach to this big-data challenge is to visualize the content of long-duration audio-recordings by calculating acoustic indices. These are statistics which describe the temporal-spectral distribution of acoustic energy and reflect content of ecological interest. We combine spectral indices to produce false-color spectrogram images. These not only reveal acoustic content but also facilitate navigation. An additional analytic challenge is to find appropriate descriptors to summarize the content of 24-hour recordings, so that it becomes possible to monitor long-term changes in the acoustic environment at a single location and to compare the acoustic environments of different locations. We describe a 24-hour 'acoustic-fingerprint' which shows some preliminary promise.

Keywords: Big Data; acoustic signal processing; data visualisation; national security; Big-data; acoustic data visualisation; acoustic energy; acoustic environment; acoustic recording; false-color spectrogram image; temporal-spectral distribution; visual fingerprint; Acoustics; Digital audio players; Entropy; Indexes; Meteorology; Monitoring; Spectrogram (ID#: 15-8808)



Lu, Yao; Chang, Ye; Tang, Ning; Qu, Hemi; Pang, Wei; Zhang, Daihua; Zhang, Hao; Duan, Xuexin, "Concentration-Independent Fingerprint Library of Volatile Organic Compounds Based on Gas-Surface Interactions by Self-Assembled Monolayer Functionalized Film Bulk Acoustic Resonator Arrays," in SENSORS, 2015 IEEE, pp. 1-4, 1-4 Nov. 2015. doi: 10.1109/ICSENS.2015.7370506

Abstract: This paper reported a novel e-nose type gas sensor based on film bulk acoustic resonator (FBAR) array in which each sensor is functionalized individually by different organic monolayers. Such hybrid sensors have been successfully demonstrated for VOCs selective detections. Two concentration-independent fingerprints (adsorption energy constant and desorption rate) were obtained from the adsorption isotherms (Ka, K1, K2) and kinetic analysis (koff) with four different amphiphilic self-assembled monolayers (SAMs) coated on high frequency FBAR transducers (4.44 GHz). The multi-parameter fingerprints regardless of concentration effects compose a recognition library and improve the selectivity of VOCs.

Keywords: Adsorption; Film bulk acoustic resonators; Fingerprint recognition; Kinetic theory; Out of order; Silicon; Transducers; ??-nose; Adsorption analysis; Concentration-independent; FBAR; SAMs; VOCs (ID#: 15-8809)



Ondel, L.; Anguera, X.; Luque, J., "MASK+: Data-Driven Regions Selection For Acoustic Fingerprinting," in Acoustics, Speech and Signal Processing (ICASSP), 2015 IEEE International Conference on, pp. 335-339, 19-24 April 2015. doi: 10.1109/ICASSP.2015.7177986

Abstract: Acoustic fingerprinting is the process to deterministically obtain a compact representation of an audio segment, used to compare multiple audio files or to efficiently search for a file within a big database. Recently, we proposed a novel fingerprint named MASK (Masked Audio Spectral Keypoints) that encodes the relationship between pairs of spectral regions around a single spectral energy peak into a binary representation. In the original proposal the configuration of location and size of the regions pairs was determined manually to optimally encode how energy flows around the spectral peak. Such manual selection has always been considered as a weakness in the process as it might not be adapted to the actual data being represented. In this paper we address this problem by proposing a unsupervised, data-driven method based on mutual information theory to automatically define an optimal MASK fingerprint structure. Audio retrieval experiments optimizing for data distorted with additive Gaussian white noise show that the proposed method is much more robust than the original MASK and a well-known acoustic fingerprint.

Keywords: AWGN; audio coding; audio databases; information retrieval; optimisation; signal representation; MASK+; Masked Audio Spectral Keypoints; acoustic fingerprinting; additive Gaussian white noise; audio files; audio retrieval experiments; audio segment; binary representation; compact representation; data-driven region selection; mutual information theory; optimal MASK fingerprint structure; spectral energy; spectral regions; Acoustics; Distortion; Mutual information; Noise measurement; Robustness; Signal to noise ratio; Audio fingerprinting; content recognition (ID#: 15-8810)



Fung, S.; Yipeng Lu; Hao-Yen Tang; Tsai, J.M.; Daneman, M.; Boser, B.E.; Horsley, D.A., "Theory and Experimental Analysis of Scratch Resistant Coating for Ultrasonic Fingerprint Sensors," in Ultrasonics Symposium (IUS), 2015 IEEE International, pp. 1-4, 21-24 Oct. 2015. doi: 10.1109/ULTSYM.2015.0150

Abstract: Ultrasonic imaging for fingerprint applications offers better tolerance of external conditions and high spatial resolution compared to typical optical and solid state sensors respectively. Similar to existing fingerprint sensors, the performance of ultrasonic imagers is sensitive to physical damage. Therefore it is important to understand the theory behind transmission and reflection effects of protective coatings for ultrasonic fingerprint sensors. In this work, we present the analytical theory behind effects of transmitting ultrasound through a thin film of scratch resistant material. Experimental results indicate transmission through 1 μm of Al2O3 is indistinguishable from the non-coated cover substrate. Furthermore, pulse echo measurements of 5 μm thick Al2O3 show ultrasound pressure reflection increases in accordance with both theory and finite element simulation. Consequently, feasibility is demonstrated of ultrasonic transmission through a protective layer with greatly mismatched acoustic impedance when sufficiently thin. This provides a guide for designing sensor protection when using materials of vastly different acoustic impedance values.

Keywords: acoustic impedance; fingerprint identification; finite element analysis; ultrasonic transducers; ultrasonic transmission; acoustic impedance; finite element simulation; pulse echo measurements; scratch resistant coating; ultrasonic fingerprint sensors; ultrasonic transmission; ultrasound pressure reflection; Acoustic measurements; Acoustics; Aluminum oxide; Coatings; Sensors; Substrates; Ultrasonic imaging; piezoelectric micromachined ultrasound transducers; ultrasonic transducers; ultrasonic transmission (ID#: 15-8811)



Hoople, J.; Kuo, J.; Abdel-moneum, M.; Lal, A., "Chipscale GHZ Ultrasonic Channels for Fingerprint Scanning," in Ultrasonics Symposium (IUS), 2015 IEEE International, pp. 1-4, 21-24 Oct. 2015. doi: 10.1109/ULTSYM.2015.0027

Abstract: In this paper we present 1-3 GHz frequency ultrasonic interrogation of surface ultrasonic impedances. The chipscale and CMOS integration of GHz transducers can enable surface identification imaging for many applications. We use aluminum nitride piezoelectric thin films driven at maximum amplitudes of 4-Vpp to launch and measure pulse packets. In this paper we first use the contrast in ultrasonic impedance between air and skin to create an image of a fingerprint. As a second application we directly measure the reflection coefficient for different liquids to demonstrate the ability to measure the ultrasonic impedance and distinguish between three different liquids. Using a rubber phantom the image of a portion of a fingerprint is captured by measuring changes in signal levels at the resonance frequency of the piezoelectric transducers 2.7 GHz. Reflected amplitude waves from air and skin differ by factors of 1.8-2. The measurements for three different liquids; water, isopropyl alcohol, and acetone show that the three liquids have sufficiently different acoustic impedances to be able to identify them.

Keywords: CMOS image sensors; aluminium compounds; fingerprint identification; phantoms; piezoelectric thin films; piezoelectric transducers; surface impedance; ultrasonic transducers; AlN; CMOS integration; aluminum nitride piezoelectric thin films; chipscale GHz ultrasonic channels; fingerprint scanning; frequency 1 GHz to 3 GHz; piezoelectric transducers; rubber phantom; surface ultrasonic impedances; Acoustics; Aluminum nitride; CMOS integrated circuits; Fingerprint recognition; Impedance; Reflection coefficient; Transducers; AlN; Fingerprint; MEMS (ID#: 15-8812)



Hon, Tsz-Kin; Wang, Lin; Reiss, Joshua D.; Cavallaro, Andrea, "Fine Landmark-Based Synchronization of Ad-Hoc Microphone Arrays," in Signal Processing Conference (EUSIPCO), 2015 23rd European, pp. 1331-1335, Aug. 31 2015-Sept. 4 2015. doi: 10.1109/EUSIPCO.2015.7362600

Abstract: We use audio fingerprinting to solve the synchronization problem between multiple recordings from an ad-hoc array consisting of randomly placed wireless microphones or handheld smartphones. Synchronization is crucial when employing conventional microphone array techniques such as beam-forming and source localization. We propose a fine audio landmark fingerprinting method that detects the time difference of arrivals (TDOAs) of multiple sources in the acoustic environment. By estimating the maximum and minimum TDOAs, the proposed method can accurately calculate the unknown time offset between a pair of microphone recordings. Experimental results demonstrate that the proposed method significantly improves the synchronization accuracy of conventional audio fingerprinting methods and achieves comparable performance to the generalized cross-correlation method.

Keywords: Array signal processing; Feature extraction; Microphone arrays; Signal processing algorithms; Synchronization; Time-frequency analysis; Synchronization; audio fingerprinting; microphone array (ID#: 15-8813)



Kohout, J.; Pevny, T., "Unsupervised Detection of Malware in Persistent Web Traffic," in Acoustics, Speech and Signal Processing (ICASSP), 2015 IEEE International Conference on, pp. 1757-1761, 19-24 April 2015. doi: 10.1109/ICASSP.2015.7178272

Abstract: Persistent network communication can be found in many instances of malware. In this paper, we analyse the possibility of leveraging low variability of persistent malware communication for its detection. We propose a new method for capturing statistical fingerprints of connections and employ outlier detection to identify the malicious ones. Emphasis is put on using minimal information possible to make our method very lightweight and easy to deploy. Anomaly detection is commonly used in network security, yet to our best knowledge, there are not many works focusing on the persistent communication itself, without making further assumptions about its purpose.

Keywords: Internet; computer network security; invasive software telecommunication traffic; anomaly detection; network security; outlier detection; persistent malware communication; persistent network communication; persistent web traffic; statistical fingerprints; unsupervised detection; Companies; Detection algorithms; Detectors; Histograms; Joints; Malware; Servers; malware; outlier detection; persistent communication (ID#: 15-8814)



Tang, H.; Lu, Y.; Fung, S.; Tsai, J.M.; Daneman, M.; Horsley, D.A.; Boser, B.E., "Pulse-Echo Ultrasonic Fingerprint Sensor on a Chip," in Solid-State Sensors, Actuators and Microsystems (TRANSDUCERS), 2015 Transducers - 2015 18th International Conference on, pp. 674-677, 21-25 June 2015. doi: 10.1109/TRANSDUCERS.2015.7181013

Abstract: A fully-integrated ultrasonic fingerprint sensor based on pulse-echo imaging is presented. The device consists of a 24×8 Piezoelectric Micromachined Ultrasonic Transducer (PMUT) array bonded at the wafer level to custom readout electronics fabricated in a 180-nm CMOS process. The proposed top-driving bottom-sensing technique minimizes signal attenuation due to the large parasitics associated with high-voltage transistors. With 12V driving signal strength, the sensor takes 24μs to image a 2.3mm by 0.7mm section of a fingerprint.

Keywords: CMOS image sensors; integrated circuit bonding; micromachining; microsensors; piezoelectric transducers; pulse measurement; readout electronics; sensor arrays; ultrasonic transducer arrays; ultrasonic variables measurement; CMOS process; PMUT array; high-voltage transistor; piezoelectric micromachined ultrasonic transducer array; pulse-echo imaging; pulse-echo ultrasonic fingerprint sensor on a chip; readout electronics; signal attenuation; size 180 mum; time 24 mus; top-driving bottom-sensing technique; voltage 12 V; wafer level bonding; Acoustics; Aluminum nitride; Arrays; Electrodes; Fingerprint recognition; Micromechanical devices; Transducers; Fingerprint sensor; MEMS-CMOS integration; PMUT; Ultrasound transducer (ID#: 15-8815)



Qi Yan; Rui Yang; Jiwu Huang, "Copy-Move Detection of Audio Recording with Pitch Similarity," in Acoustics, Speech and Signal Processing (ICASSP), 2015 IEEE International Conference on, pp. 1782-1786, 19-24 April 2015. doi: 10.1109/ICASSP.2015.7178277

Abstract: The widespread availability of audio editing software has made it very easy to create forgeries without perceptual trace. Copy-move is one of popular audio forgeries. It is very important to identify audio recording with duplicated segments. However, copy-move detection in digital audio with sample by sample comparison is invalid due to post-processing after forgeries. In this paper we present a method based on pitch similarity to detect copy-move forgeries. We use a robust pitch tracking method to extract the pitch of every syllable and calculate the similarities of these pitch sequences. Then we can use the similarities to detect copy-move forgeries of digital audio recording. Experimental result shows that our method is feasible and efficient.

Keywords: audio recording; counterfeit goods; audio editing software; audio forgeries; copy-move detection; digital audio recording; pitch sequences; pitch tracking; post-processing; Audio databases; Audio recording; Fingerprint recognition; Forgery; Image segmentation; Robustness; Security; Audio forensics; Audio forgeries; Copy-Move detection; Pitch similarity (ID#: 15-8816)



Nagano, H.; Mukai, R.; Kurozumi, T.; Kashino, K., "A Fast Audio Search Method Based on Skipping Irrelevant Signals By Similarity Upper-Bound Calculation," in Acoustics, Speech and Signal Processing (ICASSP), 2015 IEEE International Conference on, pp. 2324-2328, 19-24 April 2015. doi: 10.1109/ICASSP.2015.7178386

Abstract: In this paper, we describe an approach to accelerate fingerprint techniques by skipping the search for irrelevant sections of the signal and demonstrate its application to the divide and locate (DAL) audio fingerprint method. The search result for the applied method, DAL3, is the same as that of DAL mathematically. Experimental results show that DAL3 can reduce the computational cost of DAL to approximately 25% for the task of music signal retrieval.

Keywords: acoustic signal processing; audio signal processing; fingerprint identification; musical acoustics; DAL audio fingerprint method; divide-and-locate audio fingerprint method; fast audio search method; finger print technology; music signal retrieval; similarity upper-bound calculation; skipping irrelevant signals; Acceleration; Accuracy; Computational efficiency; Databases; Fingerprint recognition; Histograms; Multiple signal classification; Audio fingerprint; audio search; information retrieval (ID#: 15-8817)



Xu, G.; Meng, Z.; Lin, J.; Deng, C.; Carson, P.; Fowlkes, J.; Tomlins, S.; Siddiqui, J.; Davis, M.; Kunju, L.; Wang, X., "In Vivo Biopsy by PhotoacousticUS Based Tissue Characterization," in Ultrasonics Symposium (IUS), 2015 IEEE International, pp. 1-4, 21-24 Oct. 2015. doi: 10.1109/ULTSYM.2015.0216

Abstract: Our recent research has demonstrated that the frequency domain power distribution of radio-frequency (RF) photoacoustic (PA) signals contains the microscopic information of the optically absorbing materials in the sample. In this research, we were seeking for methods of systematically analyzing the PA measurement from biological tissues and the feasibility of evaluating tissue chemical and microstructural features for potential tissue characterization. By performing PA scan over a broad spectrum covering the optical fingerprints of specific relevant chemical components, and then transforming the radio-frequency signals into the frequency domain, a 2D spectrogram, namely physio-chemical spectrogram (PCS) can be generated. The PCS contains rich diagnostic information allowing quantification of not only contents but also histological microfeatures of various chemical components in tissue. Comprehensive analysis of PCS, namely photoacoustic physio-chemical analysis (PAPCA), could reveal the histopathology information in tissue and hold the potential to achieve comprehensive and accurate tissue characterization.

Keywords: bio-optics; biological tissues; biomedical ultrasonics; photoacoustic effect; biological tissues; biopsy; chemical components; frequency domain power distribution; optically absorbing materials; photoacoustic physiochemical analysis; photoacousticUS based tissue characterization; physiochemical spectrogram; radiofrequency photoacoustic signals; Acoustics; Biomedical optical imaging; Chemicals; Fingerprint recognition; Lipidomics; Liver; Microscopy; fatty liver; multi-spectral; photoacoustic imaging; prostate cancer; spectral analysis; tissue characterization (ID#: 15-8818)



Ruizhe Li; Chang-Tsun Li; Yu Guan, "A Compact Representation of Sensor Fingerprint for Camera Identification and Fingerprint Matching," in Acoustics, Speech and Signal Processing (ICASSP), 2015 IEEE International Conference on, pp. 1777-1781, 19-24 April 2015. doi: 10.1109/ICASSP.2015.7178276

Abstract: Sensor Pattern Noise (SPN) has been proved as an effective fingerprint of imaging devices to link pictures to the cameras that acquired them. In practice, forensic investigators usually extract this camera fingerprint from large image block to improve the matching accuracy because large image blocks tend to contain more SPN information. As a result, camera fingerprints usually have a very high dimensionality. However, the high dimensionality of fingerprint will incur a costly computation in the matching phase, thus hindering many interesting applications which require an efficient real-time camera matching. To solve this problem, an effective feature extraction method based on PCA and LDA is proposed in this work to compress the dimensionality of camera fingerprint. Our experimental results show that the proposed feature extraction algorithm could greatly reduce the size of fingerprint and enhance the performance in term of Receiver Operating Characteristic (ROC) curve of several existing methods.

Keywords: data compression; feature extraction; fingerprint identification; image enhancement; image forensics; image matching; image representation; image sensors; principal component analysis; LDA; PCA; camera fingerprint dimensionality compression; camera fingerprint extraction; camera identification; compact sensor fingerprint representation; feature extraction method; fingerprint matching; fingerprint size reduction; forensic investigators; image blocks; imaging devices; matching accuracy improvement; receiver operating characteristic curve; sensor pattern noise; Cameras; Principal component analysis; Digital forensics; PCA denoising; Photo-response nonuniformity noise; Sensor pattern noise}, (ID#: 15-8819)



Horsley, David A.; Rozen, Ofer; Lu, Yipeng; Shelton, Stefon; Guedes, Andre; Przybyla, Richard; Tang, Hao-Yen; Boser, Bernhard E., "Piezoelectric Micromachined Ultrasonic Transducers for Human-Machine Interfaces and Biometric Sensing," in SENSORS, 2015 IEEE, pp. 1-4, 1-4 Nov. 2015. doi: 10.1109/ICSENS.2015.7370564

Abstract: Improvements in thin-film piezoelectric materials such as AlN and PZT enable piezoelectric micromachined transducers that are superior to existing capacitive transducers. This paper presents the basic design equations, equivalent circuit model, and fabrication processes for piezoelectric micromachined ultrasonic transducers (PMUTs) operating in fluid or air. Relative to conventional ultrasonic transducers, PMUTs have the advantages of small size, low cost, low power consumption, and compatibility with integrated circuit manufacturing methods. These advantages enable PMUTs to be used in new applications such as human-machine interfaces and ultrasonic fingerprint sensors.

Keywords: Acoustics; Aluminum nitride; Electrodes; III-V semiconductor materials; Impedance; Resonant frequency; Silicon; MEMS; PMUT; piezoelectric sensors; ultrasonic transducers (ID#: 15-8820)



Valsesia, D.; Coluccia, G.; Bianchi, T.; Magli, E., "Scale-Robust Compressive Camera Fingerprint Matching with Random Projections," in Acoustics, Speech and Signal Processing (ICASSP), 2015 IEEE International Conference on, pp. 1697-1701, 19-24 April 2015. doi: 10.1109/ICASSP.2015.7178260

Abstract: Recently, we demonstrated that random projections can provide an extremely compact representation of a camera fingerprint without significantly affecting the matching performance. In this paper, we propose a new construction that makes random projections of camera fingerprints scale-robust. The proposed method maps the compressed fingerprint of a rescaled image to the compressed fingerprint of the original image, rescaled by the same factor. In this way, fingerprints obtained from rescaled images can be directly matched in the compressed domain, which is much more efficient than existing scale-robust approaches. Experimental results on the publicly available Dresden database show that the proposed technique is robust to a wide range of scale transformations. Moreover, robustness can be further improved by providing reference scales in the database, with a small additional storage cost.

Keywords: data compression; fingerprint identification; image coding; image matching; image sensors; photoresponse nonuniformity; random projections; scale-robust compressive camera fingerprint matching; Cameras; Databases; Forensics; Image coding; Robustness; Sensors; PRNU; random projections (ID#: 15-8821)



Ling Zou; Qianhua He; Xiaohui Feng, "Cell Phone Verification from Speech Recordings using Sparse Representation," in Acoustics, Speech and Signal Processing (ICASSP), 2015 IEEE International Conference on, pp. 1787-1791, 19-24 April 2015. doi: 10.1109/ICASSP.2015.7178278

Abstract: Source recording device recognition is an important emerging research field of digital media forensic. Most of the prior literature focuses on the recording device identification problem. In this study we propose a source cell phone verification scheme based on sparse representation. We employed Gaussian supervectors (GSVs) based on Mel-frequency cepstral coefficients (MFCCs) extracted from the speech recordings to characterize the intrinsic fingerprint of the cell phone. For the sparse representation, both exemplar based dictionary and dictionary learned by K-SVD algorithm were examined to this problem. Evaluation experiments were conducted on a corpus consists of speech recording recorded by 14 cell phones. The achieved equal error rate (EER) demonstrated the feasibility of the proposed scheme.

Keywords: Gaussian processes; audio recording; cepstral analysis; digital forensics; error statistics; signal representation; smart phones; speech recognition; vectors; EER; Gaussian supervectors; K-SVD algorithm; MFCC; Mel-frequency cepstral coefficients; dictionary learning; digital media forensic; equal error rate; exemplar based dictionary; recording device identification problem; source cell phone verification; sparse representation; speech recording device recognition; Cellular phones; Dictionaries; Feature extraction; Forensics; Measurement; Speech; Speech recognition; Digital audio forensic; Gaussian supervector; Source cell phone verification; Sparse representation (ID#: 15-8822)



Vezzoli, E.; Dzidek, B.; Sednaoui, T.; Giraud, F.; Adams, M.; Lemaire-Semail, B., "Role of Fingerprint Mechanics and Non-Coulombic Friction in Ultrasonic Devices," in World Haptics Conference (WHC), 2015 IEEE, pp. 43-48, 22-26 June 2015. doi: 10.1109/WHC.2015.7177689

Abstract: Ultrasonic vibration of a plate can be used to modulate the friction of a finger pad sliding on a surface. This modulation can modify the user perception of the touched object and induce the perception of textured materials. In the current paper, an elastic model of finger print ridges is developed. A friction reduction phenomenon based on non-Coulombic friction is evaluated based on this model. Then, a comparison with experimental data is carried out to assess the validity of the proposed model and analysis.

Keywords: friction; haptic interfaces; ultrasonic devices; vibrations; elastic model; finger pad sliding friction; finger print ridges; fingerprint mechanics; friction reduction phenomenon; nonCoulombic friction; textured materials; ultrasonic devices; ultrasonic vibration; user perception; Acoustics; Actuators; Fingers; Force; Friction; Springs; Vibrations (ID#: 15-8823)



Papalambrou, A.; Karadimas, D.; Gialelis, J.; Voyiatzis, A.G., "A Versatile Scalable Smart Waste-Bin System Based on Resource-Limited Embedded Devices," in Emerging Technologies & Factory Automation (ETFA), 2015 IEEE 20th Conference on, pp. 1-8, 8-11 Sept. 2015. doi: 10.1109/ETFA.2015.7301466

Abstract: This work presents the architecture, modelling, simulation, and physical implementation of a versatile, scalable system for use in common-type waste-bins that can perform and transmit accurate fill-level estimates while consuming minimal power and consisting of low-cost embedded components. The sensing units are based on ultrasonic sensors that provide ranging information which is translated to fill-level estimations based on extensive simulations in MATLAB and physical experiments. At the heart of the proposed implementation lies RFID technology with active RFID tags retrieving information and controlling the sensors and RFID readers receiving and interpreting information. Statistical processing of the simulation in combination with physical experiments and field tests verified that the system works accurately and efficiently with a tiny data-load fingerprint.

Keywords: embedded systems; radiofrequency identification; refuse disposal; statistical analysis; ultrasonic transducers; MATLAB; RFID readers; RFID technology; active RFID tags; architecture; data-load fingerprint; fill-level estimations; low-cost embedded components; minimal power consumption; modelling; physical implementation; resource-limited embedded devices; sensing units; sensors control; simulation; statistical processing; ultrasonic sensors; urban solid waste; versatile scalable smart waste-bin system; Accuracy; Acoustics; Active RFID tags; Estimation; Mobile communication; active RFID tag; smart-cities; sustainability; ultrasonic sensors; urban solid waste; waste-bin fill-level estimation (ID#: 15-8824)



Saad Zaghloul, Z.; Bayoumi, M., "Adaptive Neural Matching Online Spike Sorting VLSI Chip Design for Wireless BCI Implants," in Acoustics, Speech and Signal Processing (ICASSP), 2015 IEEE International Conference on, pp. 977-981, 19-24 April 2015. doi: 10.1109/ICASSP.2015.7178115

Abstract: Controlling the surrounding world by just the power of our thoughts has always seemed to be just a fictional dream. With recent advancements in technology and research, this dream has become a reality for some through the use of a Brain Computer/Machine Interface (BCI/BMI). One of the most important goals of BCI is to enable handicap people to control artificial limbs. Some research proposed wireless implants that do not require chronic wound in the skull. However, the communications consume a high bandwidth and power that exceeds the allowed limits, 8-10mW. This study proposes and implements a modified version of real-time spike sorting for wireless BCI [4] that simplifies and uses less computation via an adaptive neural-structure; which makes it simpler, faster and power and area efficient. The system was implemented, and simulated using Modalism and Cadence, with ideal case and worst case accuracy of 100% and 91.7%, respectively. Also, the chip layout of 0.704mm2, with power consumption of 4.7mW and was synthesized on 45nm technology using Synopsys.

Keywords: brain-computer interfaces; integrated circuit design; neural chips; prosthetics; Cadence; Modalism; Synopsys; adaptive neural matching online spike sorting VLSI chip design; artificial limbs; brain computer/machine interface; power 4.7 mW; power 8 mW to 10 mW; power consumption; size 45 nm; wireless BCI implants; wireless implants; Bandwidth; Fingerprint recognition; Implants; Neurons; Sorting; Wireless communication; Wireless sensor networks; Adaptive; BCI/BMI; Spike Sorting; VLSI; layout (ID#: 15-8825)



Varges da Silva, M.; Marana, A.N.; Paulino, A.A., "On the Importance of Using High Resolution Images, Third Level Features and Sequence of Images for Fingerprint Spoof Detection," in Acoustics, Speech and Signal Processing (ICASSP), 2015 IEEE International Conference on, pp. 1807-1811, 19-24 April 2015. doi: 10.1109/ICASSP.2015.7178282

Abstract: The successful and widespread deployment of biometric systems brings on a new challenge: the spoofing, which involves presenting an artificial or fake biometric trait to the biometric systems so that unauthorized users can gain access to places and/or information. We propose a fingerprint spoof detection method that uses a combination of information available from pores, statistical features and fingerprint image quality to classify the fingerprint images into live or fake. Our spoof detection algorithm combines these three types of features to obtain an average accuracy of 97.3% on a new database (UNESP-FSDB) that contains 4,800 images of live and fake fingerprints. An analysis is performed that considers some issues such as image resolution, pressure by the user, sequence of images and level of features.

Keywords: fingerprint identification; image resolution; image sequences; biometric systems; fingerprint spoof detection; high resolution images; image resolution; image sequence; third level features; Accuracy; Biomedical imaging; Classification algorithms; Fingerprint recognition; Image resolution; Iris recognition; Biometrics; fingerprint; pores; security; spoof detection (ID#: 15-8826)



Honghai Yu; Moulin, P., "SNR Maximization Hashing for Learning Compact Binary Codes," in Acoustics, Speech and Signal Processing (ICASSP), 2015 IEEE International Conference on, pp. 1692-1696, 19-24 April 2015. doi: 10.1109/ICASSP.2015.7178259

Abstract: In this paper, we propose a novel robust hashing algorithm based on signal-to-noise ratio (SNR) maximization to learn binary codes. We first motivate SNR maximization for robust hashing in a statistical model, under which maximizing SNR minimizes the robust hashing error probability. A globally optimal solution can be obtained by solving a generalized eigenvalue problem. The proposed algorithm is tested on both synthetic and real datasets, showing significant performance gain over existing hashing algorithms.

Keywords: binary codes; eigenvalues and eigenfunctions; error statistics; optimisation; SNR maximization hashing; compact binary codes; generalized eigenvalue problem; novel robust hashing algorithm; robust hashing error probability; signal-to-noise ratio maximization; statistical model; Arrays; Fingerprint recognition; Music; Robustness; Signal to noise ratio; Training; Robust hashing; SNR maximization; content identification; generalized eigenproblem (ID#: 15-8827)



Ouali, C.; Dumouchel, P.; Gupta, V., "Efficient Spectrogram-Based Binary Image Feature for Audio Copy Detection," in Acoustics, Speech and Signal Processing (ICASSP), 2015 IEEE International Conference on, pp. 1792-1796, 19-24 April 2015. doi: 10.1109/ICASSP.2015.7178279

Abstract: This paper presents the latest improvements on our Spectro system that detects transformed duplicate audio content. We propose a new binary image feature derived from a spectrogram matrix by using a threshold based on the average of the spectral values. We quantize this binary image by applying a tile of fixed size and computing the sum of each small square in the tile. Fingerprints of each binary image encode the positions of the selected tiles. Evaluation on TRECVID 2010 CBCD data shows that this new feature improves significantly the Spectro system for transformations that add irrelevant speech to the audio. Compared to a state-of-the-art audio fingerprinting system, the proposed method reduces the minimal Normalized Detection Cost Rate (min NDCR) by 33%, improves localization accuracy by 28% and results in 40% fewer missed queries.

Keywords: feature extraction; matrix algebra; TRECVID 2010 CBCD data; audio copy detection; audio fingerprinting system; efficient spectrogram-based binary image feature; minimal normalized detection cost rate; spectrogram matrix; Feature extraction; Fingerprint recognition; Graphics processing units; Multimedia communication; Robustness; Spectrogram; Speech; Content-based copy detection; TRECVID; audio fingerprints; spectrogram (ID#: 15-8828)




Articles listed on these pages have been found on publicly available internet pages and are cited with links to those pages. Some of the information included herein has been reprinted with permission from the authors or data repositories. Direct any requests via Email to for removal of the links or modifications to specific citations. Please include the ID# of the specific citation in your correspondence.