Search results

Section: Publications & Resources

Publication: IEEE Transactions on Audio, Speech and Language Processing

Single-channel, speaker-independent speech separation methods have recently seen great progress. However, the accuracy, latency, and computational cost of such methods remain insufficient. The majority of the previous methods have formulated the separation problem through the time–frequency representation of the mixed signal, which has several drawbacks, including the decoupling of the phase...

Section: Publications & Resources

Publication: IEEE Transactions on Audio, Speech and Language Processing

There are a number of studies about extraction of bottleneck (BN) features from deep neural networks (DNNs) trained to discriminate speakers, pass-phrases, and triphone states for improving the performance of text-dependent speaker verification (TD-SV). However, a moderate success has been achieved.

Section: Publications & Resources

Publication: IEEE Transactions on Information Forensics and Security

Automated biometric identification systems are inherently challenged to optimize false (non-)match rates. This can be addressed either by directly improving comparison subsystems, or indirectly by allowing only “good quality” biometric queries to be compared.

Section: Publications & Resources

Publication: IEEE Transactions on Information Forensics and Security

Steganographic schemes are commonly designed in a way to preserve image statistics or steganalytic features. Since most of the state-of-the-art steganalytic methods employ a machine learning (ML)-based classifier, it is reasonable to consider countering steganalysis by trying to fool the ML classifiers.

Section: Publications & Resources

Publication: IEEE Transactions on Information Forensics and Security

Current anomaly detection systems (ADSs) apply statistical and machine learning algorithms to discover zero-day attacks, but such algorithms are vulnerable to advanced persistent threat actors. In this paper, we propose an adversarial statistical learning mechanism for anomaly detection, outlier Dirichlet mixture-based ADS (ODM-ADS), which has three new capabilities.

Section: Publications & Resources

Publication: IEEE Transactions on Information Forensics and Security

Low-level criminals, who do the legwork in a criminal organization, are the most likely to be arrested, whereas the high-level ones tend to avoid attention. But crippling the work of criminal organizations is not possible unless investigators can identify the most influential, high-level members and monitor their communication channels.

Section: Publications & Resources

The list of tables of contents (TOCs) are now available for February 2019. The TOCs are formatted to the style of its publication and offers not only links to the full issue, but also to the individual articles in IEEEXplore®. 

Section: Events

Publication: IEEE Transactions on Signal and Information Processing over Networks

Manuscript Due: July 1, 2019 Publication Date: January 2020 CFP Document

Section: Publications & Resources

Image, Video, and Multidimensional Signal Processing Technical Committee (IVMSP TC) promotes and guides the advancement of the field of image, video, and multidimensional signal processing.

Lecturer/Senior Lecturer in Speech and Language Processing We are looking for candidates who will undertake original research in an area of speech technology, offer courses in this area, contribute to our thriving Masters programme in Speech & Language Processing, and supervise and recruit PhD students.