Spectrogram

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

The spectrogram correlation and transformation receiver, revisited.

Abstract: The spectrogram correlation and transformation (SCAT) receiver has been proposed as a model for the receiver structure used by fm bats. The main contribution of this paper lies in the analysis of which features of the proposed model are responsible for its high accuracy in estimating arrival times of overlapping echoes. Apart from providing an answer to this question, the analysis will also indicate the limitations of the SCAT receiver. In particular, it is shown that the temporal block of the SCAT receiver returns erroneous results for interecho delays 6 dB. It is also shown that the spectral block of the SCAT receiver generates spurious arrival times if more than two overlapping echoes are present. Finally, it is discussed how the characteristic measurement errors predicted by this analysis can be used to further investigate the accuracy of the SCAT receiver as a model of the receiver structure used by fm bats.

Classify Bird Species Audio by Augment Convolutional Neural Network

Abstract: Using convolutional neural networks, this thesis aims to create a system for fully automated identification of bird species based on spectrogram images. Spectrogram analysis is more difficult when trying to make an advance identification of a bird species. On a publicly available dataset of 8000 audio examples, we've begun by analyzing the challenges of bird species detection, segmentation, and classification to achieve our goal. It has been determined also that deep learning-based technique CNN with Fully convolutional learning calls for easier results because it eliminates the possible future modelling error caused by an imprecise knowledge of bird species and works well on coding in cohesion with the spectral analysis kernel using the librosa library. We have concluded. After obtaining the dataset from the open-source repository, it is then processed locally. For training, testing, and validation we used a subset of the dataset of 8000 sound samples. We offered a method relying on a CNN reset learned that proved to be very quick and optimum because it was first needing the spectrogram analytic kernel to learn what to class in bird species, and then it gets the system trained on features extracted. In a novel 9-step implementation, a bird species spectrogram can be detected from an audio sample. There was a loss of less than 0.0063, and the conditioning workouts accuracy is 0.9895 for the system, 0.9 as precision, and training and validation use 50 epochs in system.

Heart Sounds Separation From Lung Sounds Using Independent Component Analysis

Abstract: Heart beat is an unavoidable source of interference during lung sound recording. This disturbance is more significant at low and medium breathing flow rates. Removing heart sounds (HS) from lung sound recordings or vice versa is a challenging task but of great interest for respiratory specialists and cardiologists. In this study, to separate the two signals, a novel HS separation method based on independent component analysis (ICA) is developed. This method applies an ICA algorithm to the spectrograms of two simultaneous lung sound recordings obtained at two different locations on the chest and yields the independent spectrograms of the separated signals. Then, by implementing the inverse short time Fourier transform (ISTFT), the separated signals are reconstructed in the time domain. The method was applied to data of two healthy subjects. Analysis of the results as well as subjective inspections indicate the efficiency of the proposed method in terms of HS separation from lung sounds

A supervised classification algorithm for note onset detection

Abstract: This paper presents a novel approach to detecting onsets in music audio files. We use a supervised learning algorithm to classify spectrogram frames extracted from digital audio as being onsets or nononsets. Frames classified as onsets are then treated with a simple peak-picking algorithm based on amoving average.We present two versions of this approach. The first version uses a single neural network classifier. The second version combines the predictions of several networks trained using different hyperparameters. We describe the details of the algorithm and summarize the performance of both variants on several datasets.We also examine our choice of hyperparameters by describing results of cross-validation experiments done on a custom dataset. We conclude that a supervised learning approach to note onset detection performs well and warrants further investigation.