Narada Dilp Warakagoda

• Vedeler, Alexandra Skau & Warakagoda, Narada Dilp (2020). Generative Adversarial Immitation Learning for Steering an Unmanned Surface Vehicle. Proceedings of the Northern Lights Deep Learning Workshop.  1 . doi: 10.7557/18.5147
• Warakagoda, Narada Dilp & Midtgaard, Øivind (2020). Retrieval of similar targets in synthetic aperture sonar images with deep learning. Proceedings of meetings on acoustics.  ISSN 1939-800X.  40 . doi: 10.1121/2.0001315
• Midtgaard, Øivind; Warakagoda, Narada Dilp; Davies, Gary; Connors, Warren A. & Geilhufe, Marc (2019). Multi-phase performance evaluation for modern minehunting systems. Proceedings of SPIE, the International Society for Optical Engineering.  ISSN 0277-786X.  11012 . doi: 10.1117/12.2518837
• Warakagoda, Narada Dilp; Dirdal, Johann Alexander & Johnsen, Erlend Faxvaag (2019). Fusion of LiDAR and Camera Images in End-to-end Deep Learning for Steering an Off-road Unmanned Ground Vehicle, In Elisa Shahbazian & James Llinas (ed.),  22nd International Conference on Information Fusion.  IEEE conference proceedings.  ISBN 978-0-9964527-9-3.  0.
• Warakagoda, Narada Dilp & Midtgaard, Øivind (2018). Transfer-learning with deep neural networks for mine recognition in sonar images. Proceedings of the Institute of Acoustics.  ISSN 1478-6095.  40, s 115- 122
• Husøy, T; Pettersen, M; Nilsson, B; Öberg, T.; Warakagoda, Narada Dilp & Lie, Arne (2011). Implementation of an underwater acoustic modem with network capability, In  OCEANS, 2011 IEEE - Spain : Santander 6-9 June 2011.  IEEE conference proceedings.  ISBN 978-1-4577-0086-6.  Artikkel. Full text in Research Archive. Show summary

  This paper introduces the underwater acoustic modem as implemented within the UAN – Underwater Acoustic Network project. The low power modem has implemented turbo equalization algorithms in addition to variable spread rate direct sequence spread spectrum signaling. The network layer implemented on the modem support automatic network discovery, multi hop routing and support for mobile nodes, and when expanded with a single board computer via serial line it supports IP connectivity end-to-end. Experimental results from sea trials are presented.

View all works in Cristin

• Vedeler, Alexandra Skau & Warakagoda, Narada Dilp (2020). Generative Adversarial Immitation Learning for Steering an Unmanned Surface Vehicle.
• Warakagoda, Narada Dilp & Midtgaard, Øivind (2020). Finding similar targets in synthetic aperture sonar images with deep learning.
• Midtgaard, Øivind; Warakagoda, Narada Dilp; Davies, Gary; Connors, Warren A. & Geilhufe, Marc (2019). Multi-phase performance evaluation for modern minehunting systems.
• Warakagoda, Narada Dilp & Midtgaard, Øivind (2018). Fine-tuning of imagenet-trained deep neural networks for seafloor mine recognition in sonar images.
• Warakagoda, Narada Dilp & Johnsen, Magne Hallstein (2001). Nonlinear dynamical system based acoustic modeling for ASR.
• Warakagoda, Narada Dilp & Johnsen, Magne Hallstein (2001). Speaker adaption in an ASR system based on nonlinear dynamics.
• Warakagoda, Narada Dilp & Johnsen, Magne Hallstein (1999). Multilayer perceptron based optimal state spaced recognition for time series modelling. Show summary

  Estimating the nonlinear dynamicial system which has generated a give n time series is considered. Traditionally this is achieved via two s eparate steps: first projecting the signal frames onto the state spac e and then estimating the predictive relationship between successive state vectors. In the method presented here, these two steps are perf ormed simultaneously, where both the projection and the prediction fu nctions are represented by MLPs. In addition, a measurement function, again represented by an MLP is used. This MLP maps each state vector to a sample of the given signal. The original estimation problem is then interpreted as a training (optimization) problem, and a backprop agation type training is proposed for solving it. The method proposed is tested both with an artificial time series produced by the Henon map and a speech signal.Performance is compared with results from pop ular traditional methods, which indicates a clear superiority for our new proposed method.

• Warakagoda, Narada Dilp & Johnsen, Magne Hallstein (1999). Neural network based optimal feature extraction for ASR. Show summary

  The procedure of calculating Mel Frequency based Cepstral Coefficient s (MFCC) is shown to resemble a three layer Multilayer Perceptron (ML P) like structure. Such an MLP is employed as a preprocessor in a hyb rid HMM-MLP system, and the possibility of optimizing the whole syste m as a single entity, with respect to a suitable criterion, is pointe d out. The system, together with the Maximal Mutual Information (MMI) criterion was tested on a speaker independent, five broad class, isl oated phoneme recognition task. The reported results of these prelimi nary experiments clearly indicate the advantage of optimizable prepro cessing.

• Warakagoda, Narada Dilp & Johnsen, Magne Hallstein (1997). Dynamical system models for speech recognition. Show summary

  An approach to Automatic Speech Recognition (ASR) based on the theory of Nonlinear Dynamical systems is presented. The speech signal at a given tim considered as a scalar measurement of a the state of an unk nown multidimensional nonlinear dynamical system. Thus speech models with a small numbers of parameters are possible. Further, the concept of synchronization is introduced in order to perform robust nonlinea r prediction, i.e. with capasity to handle the highly variable nature of speech.

View all works in Cristin