Spectrogram

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

Advanced patient or elder fall detection based on movement and sound data

Abstract: The paper presents am initial implementation of a patient monitoring system that may be used for patient activity recognition and emergency treatment in case a patient or an elder falls. Sensors equipped with accelerometers and microphones are attached on the body of the patients and transmit patient movement and sound data wirelessly to the monitoring unit. Applying Short Time Fourier Transform (STFT) and spectrogram analysis on sounds detection of fall incidents is possible. The classification of the sound and movement data is performed using Support Vector Machines. Evaluation results indicate the high accuracy and the effectiveness of the proposed implementation.

Auto-term representation by the reduced interference distributions: a procedure for kernel design

Abstract: An analysis of auto-term presentation using the reduced interference distributions (RID) is done. Comparison with an ideal time-frequency signal representation is taken as a basis for this analysis. The following distributions are considered: Choi-Williams (1989), Zao-Atlas-Marks, Born-Jordan, sinc, Zhang-Sato (see ibid., vol.42, no.1, p.54, 1994), Butterworth, spectrogram, and the author's recently proposed S-method for time-frequency analysis. Various distributions produce different auto-term shapes. In all cases, the condition for cross-term reduction is contradictory to the condition for high auto-term quality. A procedure for designing a kernel that will produce the desired auto-term shape is demonstrated. An optimal kernel, with respect to the auto-term quality and cross-term suppression, is derived.

A time-frequency classifier for human gait recognition

Abstract: Radar has established itself as an effective all-weather, day or night sensor. Radar signals can penetrate walls and provide information on moving targets. Recently, radar has been used as an effective biometric sensor for classification of gait. The return from a coherent radar system contains a frequency offset in the carrier frequency, known as the Doppler Effect. The movements of arms and legs give rise to micro Doppler which can be clearly detailed in the time-frequency domain using traditional or modern time-frequency signal representation. In this paper we propose a gait classifier based on subspace learning using principal components analysis(PCA). The training set consists of feature vectors defined as either time or frequency snapshots taken from the spectrogram of radar backscatter. We show that gait signature is captured effectively in feature vectors. Feature vectors are then used in training a minimum distance classifier based on Mahalanobis distance metric. Results show that gait classification with high accuracy and short observation window is achievable using the proposed classifier.

3D CNN-Based Speech Emotion Recognition Using K-Means Clustering and Spectrograms

Abstract: Detecting human intentions and emotions helps improve human-robot interactions. Emotion recognition has been a challenging research direction in the past decade. This paper proposes an emotion recognition system based on analysis of speech signals. Firstly, we split each speech signal into overlapping frames of the same length. Next, we extract an 88-dimensional vector of audio features including Mel Frequency Cepstral Coefficients (MFCC), pitch, and intensity for each of the respective frames. In parallel, the spectrogram of each frame is generated. In the final preprocessing step, by applying k-means clustering on the extracted features of all frames of each audio signal, we select k most discriminant frames, namely keyframes, to summarize the speech signal. Then, the sequence of the corresponding spectrograms of keyframes is encapsulated in a 3D tensor. These tensors are used to train and test a 3D Convolutional Neural network using a 10-fold cross-validation approach. The proposed 3D CNN has two convolutional layers and one fully connected layer. Experiments are conducted on the Surrey Audio-Visual Expressed Emotion (SAVEE), Ryerson Multimedia Laboratory (RML), and eNTERFACE'05 databases. The results are superior to the state-of-the-art methods reported in the literature.

Principal components generalized projections: a review [Invited]

Abstract: Frequency-resolved optical gating (FROG) is a technique used to measure ultrafast laser pulses by optically producing a spectrogram, or FROG trace, of the measured pulse. While a great deal of information about the pulse can be gleaned from its FROG trace, quantitative pulse information must be obtained using an iterative two-dimensional phase retrieval algorithm. A general spectrogram/sonogram inversion algorithm called principal components generalized projections (PCGP) that can be applied to pulse measurement schemes, such as FROG, is reviewed. The algorithm is fast, robust, and can invert FROG traces in real time, making commercial pulse measurement systems based on FROG a reality. Measurement rates are no longer algorithm limited; they are data-acquisition limited. Also, because of some of its unique properties, the PCGP algorithm has found applications in measuring attosecond pulses and measuring telecommunications pulses. In addition, the PCGP structures the inversion and measurement process in a way that can allow new insights into convergence properties of spectrogram and sonogram inversion algorithms.