Topic
Spectrogram
About: Spectrogram is a research topic. Over the lifetime, 5813 publications have been published within this topic receiving 81547 citations.
Papers published on a yearly basis
Papers
More filters
Posted Content•
TL;DR: This paper compares classical methods from signal detection theory and machine learning to several deep learning architectures and finds that a three-layer convolutional neural network offers a superior tradeoff between accuracy and computational complexity.
Abstract: In the United States, the Federal Communications Commission has adopted rules permitting commercial wireless networks to share spectrum with federal incumbents in the 3.5~GHz Citizens Broadband Radio Service band. These rules require commercial systems to vacate the band when sensors detect radars operated by the U.S. military; a key example being the SPN-43 air traffic control radar. Such sensors require highly-accurate detection algorithms to meet their operating requirements. In this paper, using a library of over 14,000 3.5~GHz band spectrograms collected by a recent measurement campaign, we investigate the performance of thirteen methods for SPN-43 radar detection. Namely, we compare classical methods from signal detection theory and machine learning to several deep learning architectures. We demonstrate that machine learning algorithms appreciably outperform classical signal detection methods. Specifically, we find that a three-layer convolutional neural network offers a superior tradeoff between accuracy and computational complexity. Last, we apply this three-layer network to generate descriptive statistics for the full 3.5~GHz spectrogram library. Our findings highlight potential weaknesses of classical methods and strengths of modern machine learning algorithms for radar detection in the 3.5~GHz band.
24 citations
TL;DR: This paper presents an alternative pragmatic approach to identifying chaos using response frequency characteristics and extending the concept of the spectrogram and it is shown to work well on both experimental and simulated time series.
Abstract: The sign of the largest Lyapunov exponent is the fundamental indicator of chaos in a dynamical system. However, although the extraction of Lyapunov exponents can be accomplished with (necessarily noisy) experimental data, this is still a relatively data-intensive and sensitive endeavor. This paper presents an alternative pragmatic approach to identifying chaos using response frequency characteristics and extending the concept of the spectrogram. The method is shown to work well on both experimental and simulated time series.
24 citations
01 Jan 2006
TL;DR: A new robust adaptive tool for new born infant cry analysis is proposed, characterised by high tracking capability, well suited for the signals under study, and does not need any manual setting of whatever option to be made by the user, thus being easily usable also by non- experts.
Abstract: In this paper, a new robust adaptive tool for new- born infant cry analysis is proposed, characterised by high tracking capability, well suited for the signals under study. It performs F0, noise and resonance frequencies tracking, on signal frames of varying length (even few ms), adaptively tailored to varying signal characteristics. Moreover, voiced/unvoiced separation is implemented, allowing disregarding unvoiced parts of the signal where misleading results could be obtained. Plots of F0 and its harmonics, noise tracking, spectrogram with resonance frequencies superimposed, are presented in a coloured-scale. Some added statistics allow further understanding and comparison of results. The new software tool is completely automatic, working with any sampling frequency and F0, and also with strongly corrupted signals, and does not need any manual setting of whatever option to be made by the user, thus being easily usable also by non-experts. Some examples are reported, concerning both healthy and pathological new-born infant cries.
24 citations
TL;DR: A data-driven unsupervised learning algorithm called Intrinsic Spectral Analysis is presented designed to recover from a stream of unannotated and unsegmented audio a set of nonlinear basis functions for the speech manifold that defines a novel acoustic representation that is demonstrated to have phonological significance.
Abstract: It has long been posited that the space of speech sounds is inherently low dimensional, the result of a relatively small number of degrees of freedom involved in the human vocal apparatus. We attempt to formalize this notion by analyzing a simple physical model of the vocal tract and demonstrating that it produces transfer functions whose spectra are restricted to low dimensional manifolds embedded in an infinite dimensional space of square integrable functions. While source convolution and channel distortion precludes analytic recovery of the articulatory configuration from the observed signal, we present a data-driven unsupervised learning algorithm called Intrinsic Spectral Analysis designed to recover from a stream of unannotated and unsegmented audio a set of nonlinear basis functions for the speech manifold. Projecting a traditional spectrogram onto this nonlinear basis defines a novel acoustic representation that is demonstrated to have phonological significance, improved phonetic separability, inherent speaker independence, and complementarity with standard acoustic front-ends.
24 citations
TL;DR: In this paper, the conditions imposed on the spectrum of an emitted signal for which the interferometric method of detecting a moving sound source in shallow water is applicable for vector-scalar receivers are discussed.
Abstract: The paper discusses the conditions imposed on the spectrum of an emitted signal for which the interferometric method of detecting a moving sound source in shallow water is applicable for vector-scalar receivers. It is shown that a normalized spectrogram representing a two-dimensional Fourier transform of the interferometric pattern is identical for all four acoustic field components and combinations thereof. Results of a field experiment in which a vector-scalar receiver was applied are presented. The interference immunity of the method is considered for different field components in the case of isotropic interference.
24 citations