Can Deep Neural Networks (DNNs) provide the basis for Artificial General Intelligence (AGI) is the topic for this workshop. We do not expect to come to a specific conclusion, but what we provide here are some talks, and space for discussion. However, the speakers seem to have lined up on one side of the division (from my reading of their abstracts), so I propose to take the other side! But what...

Time multiplexed implementations of the recursive DCT processors are widely used in many multimedia and compression applications. Recently proposed three Goertzel kernels offer significant improvement (up to 90 %) in the noise performance of the time-multiplexed architecture to allow word-length specifications get reduced. In this paper, a highly optimized reconfigurable DCT architecture is pro...

Bioimpedance measurement is a non-invasive, radiation-free, and inexpensive method for measuring the electrical properties of biological tissues. In applications where transients occur, commonly used swept sinewave replaced with broadband signals such as multisine. This makes signal generation extraction real imaginary parts impedance challenging. this brief, an alternative to traditional fast ...

Development of robust and efficient front-end is crucial for robust ASR. Proper time and frequency resolution of the TFR of speech, motivated by the auditory models is considered an important factor for robustness. An efficient method of realizing a variable resolution TFR using DTFT/Goertzel algorithm is proposed instead of the standard FFT based approach. It is shown that the new representati...

An adaptive-passive quarter-wave tube resonator silencer was experimentally tested using recorded in-duct reciprocating engine exhaust noise. The exhaust noise was re-played through a loudspeaker attached to one end of a duct, and the adaptive passive system was able to track changes in engine speed and provide attenuation of the noise at the fundamental firing frequency of the engine and the t...

This paper will look at an approach that uses symmetric properties of the basis function to remove redundancies in the calculation of discrete Fourier transform (DFT). We will develop an algorithm, called the quick Fourier transform (QFT), that will reduce the number of oating point operations necessary to compute the DFT by a factor of two or four over direct methods or Goertzel's method for p...