Spectrogram

About: Spectrogram is a research topic. Over the lifetime, 5813 publications have been published within this topic receiving 81547 citations.

Sound source separation based on non-negative tensor factorization incorporating spatial cue as prior knowledge

Abstract: This paper concerns a new method of source separation that uses a spatial cue given by a user or from accompanying images to extract a target sound. The algorithm is based on non-negative tensor factorization (NTF), which decomposes multichannel spectrograms into three matrices. The components of one of the three matrices represent spatial information and are associated with the spatial cue, thus indicating which bins of the spectrogram should be given preference. When a spatial cue is available, this method has a great advantage over conventional PARAFAC-NTF in terms of both computational costs and separation quality, as measured by evaluation metrics such as SDR, SIR and SAR.

Marine Mammal Species Classification Using Convolutional Neural Networks and a Novel Acoustic Representation

Abstract: Research into automated systems for detecting and classifying marine mammals in acoustic recordings is expanding internationally due to the necessity to analyze large collections of data for conservation purposes. In this work, we present a Convolutional Neural Network that is capable of classifying the vocalizations of three species of whales, non-biological sources of noise, and a fifth class pertaining to ambient noise. In this way, the classifier is capable of detecting the presence and absence of whale vocalizations in an acoustic recording. Through transfer learning, we show that the classifier is capable of learning high-level representations and can generalize to additional species. We also propose a novel representation of acoustic signals that builds upon the commonly used spectrogram representation by way of interpolating and stacking multiple spectrograms produced using different Short-time Fourier Transform (STFT) parameters. The proposed representation is particularly effective for the task of marine mammal species classification where the acoustic events we are attempting to classify are sensitive to the parameters of the STFT.

Sign Language Gesture Recognition Using Doppler Radar and Deep Learning

Abstract: In this paper, we study American sign language (ASL) hand gesture recognition using Doppler radar. A set of ASL hand gesture motions are captured as micro- Doppler signals using a microwave X-band Doppler radar transceiver. We apply joint time-frequency analysis and observe the presence of the micro- Doppler signatures in the spectrogram. The micro- Doppler signatures of different hand gestures are analyzed using Matlab. Each hand gesture is observed to contain unique spectral characteristics. Based on unique spectral characteristics, we investigate the classification of ASL essential short phrases including emergency signals. For recognizing and characterizing the presence of micro-Doppler signatures in spectrogram we explore deep convolution neural network (DCNN) algorithm. We show that the DCNN algorithm can classify different sign language gestures based on the presence of micro- Doppler signatures in the spectrogram with fairly high accuracy. Experimental results reveal that utilizing 80% of data for training, and the remaining 20% for validation purposes in DCNN algorithm a validation accuracy of 87.5% is achieved. To further improve the recognition system, we apply a very deep learning algorithm VGG-16 using transfer learning, which improves the validation accuracy to 95%.

Application of time-frequency analysis to machinery condition assessment

Abstract: Machinery condition has traditionally been assessed by analysis of the spectral energy density of the machine's vibration signal. Examination of time-frequency representations (TFRs) of constant-speed machinery data reveals vibration features that demonstrate variation in frequency over a short time period and thus cannot be adequately characterized by the power spectrum. These features may be used as supplemental information to assess the condition of the machine. Although the spectrogram provides a general indication of the time-varying spectrum, new representations such as the "cone-kernel" TFR reveal the existence of fine structural details inherent to the signal. >

A New Time-Frequency Spectrogram Analysis of FH Signals by Image Enhancement and Mathematical Morphology

Abstract: A new method is proposed to extract the parameters of frequency hopping (FH) signals. After short-time Fourier transform (STFT), the time-frequency spectrogram of FH signals is treated as a kind of digital image with special contents. The spectrogram analysis is investigated to detect and extract FH parameters by useful image enhancement techniques and mathematical morphology. First, the spectrogram image is enhanced by contrast stretch and binarization. Then, morphological closing and opening cascaded operations are manipulated using rectangular structure elements horizontally and vertically. After morphological image processing, the spectrogram edges are extracted by boundary tracking and extraction. Finally, the important FH parameters, such as hopping carrier frequency, hop timing and hop rate can be estimated, which lay the foundations for later finer hopping frequency location. The experimental results and analysis on the short-wave FH signals show the good performance of the proposed method.