Deep neural networks (DNN) have been successfully applied for music classification tasks including music tagging. In this paper, we investigate the effect of audio preprocessing on music tagging with neural networks. We perform comprehensive experiments involving audio preprocessing using different time-frequency representations, logarithmic magnitude compression, frequency weighting and scalin...

The paper gives an automated procedure to design rational decimation compression systems that resample two-dimensional bandpass signals at their Nyquist rates. The procedure takes a sketch of the passband in the frequency domain, circumscribes it with a parallelogram, and linearly maps the parallelogram onto one period of the frequency domain. Thus, the compression system only has linear compon...

This paper develops a steganography-based paradigm for lossless-quality compression of high-resolution color images acquired by megapixel cameras. Our scheme combines space-domain and frequency-domain image processing operations where in the space domain, color-brightness separation is exploited, and in the frequency domain, spectral properties of the Fourier magnitude and phase of the color im...

Auditory compression was estimated at 250 and 4000 Hz by using the additivity of forward masking technique, which measures the effects on signal threshold of combining two temporally nonoverlapping forward maskers. The increase in threshold in the combined-masker condition compared to the individual-masker conditions can be used to estimate compression. The signal was a 250 or 4000 Hz tone burs...

of Thesis Presented to the Graduate School of the University of Florida in Partial Fulfillment of the Requirements for the Degree of Master of Science SYNERGISTIC INTEGRATION OF CODE COMPRESSION AND ENCRYPTION IN EMBEDDED SYSTEMS By Kartik Shrivastava August 2010 Chair: Prabhat Kumar Mishra Major: Computer Engineering Embedded systems are used in a wide variety of places today, from cell phones...

ECG data compression has been one of the active research areas in biomedical engineering. In this paper a compression method for electrocardiogram (ECG) signals using wavelet transform is proposed. Wavelet transform compact the energy of signal in fewer samples and has a good localization property in time and frequency domain. The MIT-BIH ECG signals are decomposed using discrete wavelet transf...

The stage after the Burrows-Wheeler Transform (BWT) has a key function inside the Burrows-Wheeler compression algorithm as it transforms the BWT output from a local context into a global context. This paper presents the Incremental Frequency Count stage, a post-BWT stage. The new stage is paired with a run length encoding stage between the BWT and entropy coding stage of the algorithm. It offer...

This paper describes the compression of grayscale medical ultrasound images using a new compression technique, space-frequency segmentation. This method finds the rate-distortion optimal representation of an image from a large set of possible space-frequency partitions and quantizer combinations. The method is especially effective when the images to code are statistically inhomogeneous, which i...

Images require substantial storage and transmission resources, thus image compression is advantageous to reduce these requirements. The objective of this paper is to evaluate a set of wavelets for image compression. Image compression using wavelet transforms results in an improved compression ratio. Wavelet transformation is the technique that provides both spatial and frequency domain informat...

Compression and noncompression amplification were compared for a range of conditions. The noncompression conditions included flat-frequency response and "LDL frequency response," with and without peak clipping. The compression conditions included a single-band compression system and two combinations of a two-channel compression system. The LDL frequency response was obtained by finding the LDL ...