Singular Spectrum Analysis for Source Separation in Drone-Based Audio Recording

Encinas, Francisco García; Silva, Luís Augusto; Mendes, André Sales; González, Gabriel Villarrubia; Leithardt, Valderi Reis Quietinho; Santana, Juan Francisco de Paz

doi:10.1109/access.2021.3065775

Cited by 7 publications

(4 citation statements)

References 44 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Regarding human-generated sounds, applications include automatic speech recognition (ASR), speaker identification (SID) [7], and music information retrieval (MIR) [8]. Research on noise reduction has been done using blind source separation (BSS) techniques [9]. Machine learning, including both 'traditional' (classic) methods as well as deep learning, has been employed to support sound recognition.…”

Section: Sound Classificationmentioning

confidence: 99%

Comparison of Pre-Trained CNNs for Audio Classification Using Transfer Learning

Tsalera

Papadakis

Σαμαράκου

2021

JSAN

View full text Add to dashboard Cite

The paper investigates retraining options and the performance of pre-trained Convolutional Neural Networks (CNNs) for sound classification. CNNs were initially designed for image classification and recognition, and, at a second phase, they extended towards sound classification. Transfer learning is a promising paradigm, retraining already trained networks upon different datasets. We selected three ‘Image’- and two ‘Sound’-trained CNNs, namely, GoogLeNet, SqueezeNet, ShuffleNet, VGGish, and YAMNet, and applied transfer learning. We explored the influence of key retraining parameters, including the optimizer, the mini-batch size, the learning rate, and the number of epochs, on the classification accuracy and the processing time needed in terms of sound preprocessing for the preparation of the scalograms and spectrograms as well as CNN training. The UrbanSound8K, ESC-10, and Air Compressor open sound datasets were employed. Using a two-fold criterion based on classification accuracy and time needed, we selected the ‘champion’ transfer-learning parameter combinations, discussed the consistency of the classification results, and explored possible benefits from fusing the classification estimations. The Sound CNNs achieved better classification accuracy, reaching an average of 96.4% for UrbanSound8K, 91.25% for ESC-10, and 100% for the Air Compressor dataset.

show abstract

Section: Sound Classificationmentioning

confidence: 99%

Comparison of Pre-Trained CNNs for Audio Classification Using Transfer Learning

Tsalera

Papadakis

Σαμαράκου

2021

JSAN

View full text Add to dashboard Cite

show abstract

“…After the relevant parameters of audio collection are set on the front panel, the mono channel is configured in the way of continuous sampling. The serial communication baud rate is 9600, and the sampling frequency is 95kHz [16][17][18]. After the sound card is set, the audio signal is saved in the "wav" format, and different voltages are applied to the insulating cylinder, insulating sleeve and insulating porcelain bottle of the ring network cabinet to store the collected data according to different components, so as to achieve accurate identification of discharge data.…”

Section: Collect Partial Discharge Data Of Intelligent Ring Network C...mentioning

confidence: 99%

Discharging state recognition method of intelligent ring network cabinet based on audio signal spectrum analysis

Zhang,

Hu,

2023

Third International Conference on Image Processing and Intelligent Control (IPIC 2023)

View full text Add to dashboard Cite

The conventional discharge state identification method mainly focuses on partial identification. The field identification environment is subject to various interference signals from Getang, resulting in poor performance of the ring main unit discharge state identification. Therefore, an intelligent ring network cabinet discharge state recognition method based on audio signal spectrum analysis is designed. Collect the partial discharge data of the intelligent ring network cabinet, and extract the characteristics of the partial discharge of the intelligent ring network cabinet. Based on the audio signal spectrum analysis, the partial discharge noise signal of the ring main unit is processed, and the discharge noise signal is filtered to ensure accurate identification of the discharge signal. By means of comparative experiments, it is verified that the recognition effect of this method is better and can be applied to real life.

show abstract

“…In [16], Blind Source Separation (BSS) approaches were adopted, namely the Singular Spectrum Analysis (SSA) algorithm, to solve the challenge of eliminating drone noise from single-channel audio recordings. This work introduced an algorithm optimization with an O(nt) spatial complexity where n was the number of sources to reconstruct and t was the signal length.…”

Section: Related Workmentioning

confidence: 99%

Ensemble System of Deep Neural Networks for Single-Channel Audio Separation

2023

View full text Add to dashboard Cite

Speech separation is a well-known problem, especially when there is only one sound mixture available. Estimating the Ideal Binary Mask (IBM) is one solution to this problem. Recent research has focused on the supervised classification approach. The challenge of extracting features from the sources is critical for this method. Speech separation has been accomplished by using a variety of feature extraction models. The majority of them, however, are concentrated on a single feature. The complementary nature of various features have not been thoroughly investigated. In this paper, we propose a deep neural network (DNN) ensemble architecture to completely explore the complimentary nature of the diverse features obtained from raw acoustic features. We examined the penultimate discriminative representations instead of employing the features acquired from the output layer. The learned representations were also fused to produce a new features vector, which was then classified by using the Extreme Learning Machine (ELM). In addition, a genetic algorithm (GA) was created to optimize the parameters globally. The results of the experiments showed that our proposed system completely considered various features and produced a high-quality IBM under different conditions.

show abstract

Singular Spectrum Analysis for Source Separation in Drone-Based Audio Recording

Cited by 7 publications

References 44 publications

Comparison of Pre-Trained CNNs for Audio Classification Using Transfer Learning

Comparison of Pre-Trained CNNs for Audio Classification Using Transfer Learning

Discharging state recognition method of intelligent ring network cabinet based on audio signal spectrum analysis

Ensemble System of Deep Neural Networks for Single-Channel Audio Separation

Contact Info

Product

Resources

About