Isolated word recognition using time-delay neural networks

Download
015520.pdf
1991
Alim, Alp
Show full item record
53
views
0
downloads
https://hdl.handle.net/11511/8408
Graduate School of Natural and Applied Sciences, Thesis

Suggestions

Isolated and connected digit recognition system for Turkish
Haydar, Ali; Demirekler, Mübeccel; Department of Electrical and Electronics Engineering (1994)
Multiple Sound Source Localization with Rigid Spherical Microphone Arrays via Residual Energy Test
Coteli, Mert Burkay; Hacıhabiboğlu, Hüseyin (2019-05-01)
The estimation of the directions-of-arrival (DOAs) of multiple sound sources is a fundamental stage in acoustic scene analysis. Many application areas such as robot audition and object-based audio (OBA) broadcast require that DOA estimation is computationally efficient to allow real-time operation. We propose a new DOA estimation approach based on a sparse representation of recorded sound fields as a linear combination of spatially bandlimited impulses in this paper. The proposed algorithm operates on a tim...
Disconnected skeletons for shape recognition
Aslan, Çağrı; Adalı, Orhan; Department of Computer Engineering (2005)
This study presents a new shape representation scheme based on disconnected symmetry axes along with a matching framework to address the problem of generic shape recognition. The main idea is to define the relative spatial arrangement of local symmetry axes in a shape centered coordinate frame. The resulting descriptions are invariant to scale, rotation, small changes in viewpoint and articulations. Symmetry points are extracted from a surface whose level curves roughly mimic the motion by curvature. By inc...
Unfolded Hybrid Beamforming With GAN Compressed Ultra-Low Feedback Overhead
Balevi, Eren; Andrews, Jeffrey G. (2021-12-01)
Optimizing a hybrid beamforming transmitter is a non-convex problem and requires channel state information, leading in most cases to nontrivial feedback overhead. We propose a methodology relying on the principles of deep generative models and unfolding to achieve near-optimal hybrid beamforming with reduced feedback and computational complexity. We first represent the channel as a low-dimensional manifold via a generative adversarial network (GAN) and search the optimum digital and analog precoders in this...
Single-molecule-resolution ultrafast near-field optical microscopy via plasmon lifetime extension
Ovalı, Rasim Volga ; Şahin, Ramazan; Bek, Alpan; Taşgın, Mehmet Emre (2021-06-14)
Metal nanostructures support plasmon oscillations on their surfaces, which normally decay very quickly. Nevertheless, the lifetime of these oscillations can be extended near a longer lifetime particle, e.g., a molecule. We utilize this phenomenon for ultrahigh (single-molecule) resolution ultrafast apertureless (scattering) applications. We demonstrate the phenomenon with the numerical solutions of 3D Maxwell equations. We use a nm-sized quantum emitter (QE) for the long lifetime particle. We place the QE a...
Citation Formats
A. Alim, “Isolated word recognition using time-delay neural networks,” Middle East Technical University, 1991.
METU IIS - Integrated Information Service open@metu.edu.tr