P
Peter Jancovic
Researcher at University of Birmingham
Publications - 87
Citations - 1070
Peter Jancovic is an academic researcher from University of Birmingham. The author has contributed to research in topics: Hidden Markov model & Speaker recognition. The author has an hindex of 16, co-authored 83 publications receiving 966 citations. Previous affiliations of Peter Jancovic include Queen's University Belfast.
Papers
More filters
Journal ArticleDOI
Automatic ground target classification using forward scattering radar
TL;DR: In this article, an experimental study is undertaken of the feasibility of forward scattering radar (FSR) and its application to automatic ground target classification, which extracts features from the radar measurements by using Fourier transform and principle component analysis and uses a nearest neighbor classifier.
Journal ArticleDOI
Automatic Detection and Recognition of Tonal Bird Sounds in Noisy Environments
Peter Jancovic,Munevver Kokuer +1 more
TL;DR: The proposed detection method shows high detection accuracy of bird tonal components and significant recognition accuracy improvements over the Mel-frequency cepstral coefficients, in both standard and noise-compensated models, and strong robustness to mismatch between the training and testing conditions.
Journal ArticleDOI
Automatic speaker, age-group and gender identification from children’s speech
TL;DR: The performances of several classification methods are compared, including Gaussian Mixture Model–Universal Background Model (GMM–UBM), GMM–Support Vector Machine (G MM–SVM) and i-vector based approaches, and the utility of different frequency bands for speaker, age-group and gender recognition from children’s speech is assessed.
Proceedings ArticleDOI
The concept of a forward scattering micro-sensors radar network for situational awareness
M. Antoniou,V. Sizov,Cheng Hu,Peter Jancovic,Raja Syamsul Azmir Raja Abdullah,Nur Emileen Abdul Rashid,Mikhail Cherniakov +6 more
TL;DR: The concept of a novel forward scattering micro-radar wireless network for ground targets detection and recognition is presented and signal processing strategies used for target detection, parameter estimation and automatic target recognition are briefly explained and supported with experimental results.
Journal ArticleDOI
Robust speech recognition using probabilistic union models
TL;DR: The theory and implementation of the probabilistic union model, and a combination of the union model with conventional noise reduction techniques to deal with a mixture of stationary noise and unknown, nonstationary noise, are introduced.