1,721,017 research outputs found
Multiplierless digital learning algorithm for cellular neural networks
Full text linkA new learning algorithm is proposed for space-varying cellular neural networks, used to implement associative memories. The algorithm exhibits some peculiar features which make it very attractive: the finite precision of connection weights is automatically taken into account as a design constraint; no multiplication is needed for weight computation; learning can be implemented in fixed point digital hardware or simulated on a digital computer without numerical errors
NMF based dictionary learning for automatic transcription of polyphonic piano music
Full text linkMusic transcription consists in transforming the musical content of audio data into a symbolic
representation. The objective of this study is to investigate a transcription system for polyphonic piano. The
proposed method focuses on temporal musical structures, note events and their main characteristics: the attack
instant and the pitch. Onset detection exploits a time-frequency representation of the audio signal. Feature
extraction is based on Sparse Nonnegative Matrix Factorization (SNMF) and Constant Q Transform (CQT),
while note classification is based on Support Vector Machines (SVMs). Finally, to validate our method, we
present a collection of experiments using a wide number of musical pieces of heterogeneous style
Associative memory design for 256 gray-level images using a multilayer neural network
Full text linkA design procedure is presented for neural associative memories storing gray-scale images. It is an evolution of a previous work based on the decomposition of the image with 2(L) gray levels into L binary patterns, stored in L uncoupled neural networks. In this letter, an L-layer neural network is proposed with both intralayer and interlayer connections. The connections between different layers introduce interactions among all the neurons, increasing the recall performance with respect to the uncoupled case. In particular, the proposed network can store images with the commonly used number of 256 gray levels instead of 16, as in the previous approach
On the use of memory for detecting musical notes in polyphonic piano music
No full textMusic transcription consists in transforming the musical content of audio data into a symbolic representation. The objective of this study is to investigate a transcription system for polyphonic piano. The proposed method focuses on temporal musical structures, note events and their main characteristics: the attack instant and the pitch. Onset detection exploits a time-frequency representation of the audio signal. Note classification is based on constant Q transform (CQT) and support vector machines (SVMs). Finally, to validate our method, we present a collection of experiments using a wide number of musical pieces of heterogeneous style
Cellular neural network template for rotation of grey-scale images
Full text linkA method for grey-scale image rotation using cellular neural networks (CNNs) is proposed. The rationale of the method is the conversion of image rotation into a small rotation followed by a sequence of translations of pixel blocks. The same programmable 3 × 3 space-varying template can be used in both cases
Analogic CNN algorithm for estimating position and size of moving objects
Full text linkAn analogic CNN algorithm is proposed for detection of multiple moving objects in high resolution, grey-scale images taken from a fixed camera. The algorithm, based on simple 3 x 3 templates, can be implemented using CNN hardware, providing the real-time operation required in surveillance and traffic control applications. Efficient separation of moving objects from the background is obtained through automatic threshold selection. The performance of the proposed method is shown using real-life indoor and outdoor video sequences. Copyright (C) 2004 John Wiley Sons, Ltd
Neural associative memory storing gray-coded gray-scale images
Full text linkIn this paper, we present a neural associative memory storing gray-scale images. The proposed approach is based on a suitable decomposition of the gray-scale image into, gray-coded binary images, stored in brain-state-in-a-box-type binary neural networks. Both learning and recall can be implemented by parallel computation, with time saving. The learning algorithm, used to store the binary images, guarantees asymptotic stability of the stored patterns, low computational cost, and control of the weights precision. Some design examples and computer simulations are presented to show the effectiveness of the proposed method
A Novel Sensor Interface for Detecting Musical Notes of Percussive Pitched Instruments
No full textWe propose a novel sensor interface for detecting notes in the musical audio signals, particularly with reference to polyphonic music of percussive pitched musical instruments. Our sensor interface is able to transform acoustic pressure, caused by a sound wave, into a musical score, that is a symbolic representation of musical notes. We focuses on note events and their main characteristics: the onset (note attack instant) and the pitch (note name). Signal processing techniques based on the Constant-Q Transform (CQT) are used to create a time-frequency representation of the signal. In particular, we propose a supervised classification methods based on Support Vector Machine (SVM) to detect pitch. Instead, our onset detection algorithm exploits a Short Time Fourier Transform (STET) representation of the audio signal. Finally, to validate our method, we present a collection of experiments using a wide number of musical pieces of heterogeneous styles
Transcription of polyphonic piano music by means of memory-based classification method
No full textMusic transcription consists in transforming the musical content of audio data into a symbolic representation. The objective of this study is to investigate a transcription system for polyphonic piano. The proposed method focuses on temporal musical structures, note events and their main characteristics: the attack instant and the pitch. Onset detection exploits a time-frequency representation of the audio signal. Note classification is based on constant Q transform (CQT) and support vector machines (SVMs). Finally, to validate our method, we present a collection of experiments using a wide number of musical pieces of heterogeneous styles
- …
