36,735 Hits in 4.5 sec

Deep Convolutional Neural Networks For Environmental Sound Classification

2022 International Journal for Research in Applied Science and Engineering Technology  
Abstract: We propose a model to classify environmental sounds such as People Sounds, Vehicles Sounds, Siren Sounds, Horn, Engine Sounds.  ...  We perform Data Augmentation techniques to extract best features from the given audio to classify which class of sound.  ...  Deep-CNN trained on the recorded dataset. Table1 shows the results comparison of some previous studies conducted for sound classification using spectrogram features.  ... 
doi:10.22214/ijraset.2022.45778 fatcat:46wwpkuslba3rhvhfdjjmjchxa

Deep Learning for Audio Signal Processing

Hendrik Purwins, Bo Li, Tuomas Virtanen, Jan Schluter, Shuo-Yiin Chang, Tara N Sainath
2019 IEEE Journal on Selected Topics in Signal Processing  
Given the recent surge in developments of deep learning, this article provides a review of the state-of-the-art deep learning techniques for audio signal processing.  ...  Subsequently, prominent deep learning application areas are covered, i.e. audio recognition (automatic speech recognition, music information retrieval, environmental sound detection, localization and tracking  ...  Since the analysis of environmental sounds is a less established research field in comparison to speech and music, the size and diversity of available datasets for developing systems is more limited in  ... 
doi:10.1109/jstsp.2019.2908700 fatcat:oy2qixj2dfe6hns7r7av6fw2wm

Field-Applicable Pig Anomaly Detection System Using Vocalization for Embedded Board Implementations

Minki Hong, Hanse Ahn, Othmane Atif, Jonguk Lee, Daihee Park, Yongwha Chung
2020 Applied Sciences  
and converts them into spectrograms; and (3) A pig anomaly detection module based on MnasNet, a lightweight deep learning method, to which the 8-bit filter clustering method proposed in this study is  ...  The system consists of a pipeline structure, starting from sound acquisition to abnormal situation detection, and can be installed and operated in an actual pig farm.  ...  Conflicts of Interest: The authors declare no conflict of interest.  ... 
doi:10.3390/app10196991 fatcat:mpnazlosbjaqzlqmktd665jsru

A Comparison of deep learning methods for environmental sound [article]

Juncheng Li, Wei Dai, Florian Metze, Shuhui Qu, Samarjit Das
2017 arXiv   pre-print
Environmental sound detection is a challenging application of machine learning because of the noisy nature of the signal, and the small amount of (labeled) data that is typically available.  ...  This work thus presents a comparison of several state-of-the-art Deep Learning models on the IEEE challenge on Detection and Classification of Acoustic Scenes and Events (DCASE) 2016 challenge task and  ...  In this paper, we present a comparison of the most successful and complementary approaches to sound event detection on DCASE, which we implemented on top of our evaluation system [6] in a systematic  ... 
arXiv:1703.06902v1 fatcat:wfb43bjr2zfkvhnpwg4vl7vyna

Automatic Environmental Sound Recognition (AESR) Using Convolutional Neural Network

Md. Rayhan Ahmed, Department of Computer Science and Engineering, Stamford University Bangladesh, Dhaka, Bangladesh, Towhidul Islam Robin, Ashfaq Ali Shafin
2020 International Journal of Modern Education and Computer Science  
We can convert a short audio file of a sound event into a spectrogram image and feed that image to the Convolutional Neural Network (CNN) for processing.  ...  Our study also shows a comparative analysis between the Adaptive Learning Rate Optimizer (Adam) and RAdam optimizer used in training the model to correctly classifying the environmental sounds from image  ...  Acknowledgment The authors would like to acknowledge the anonymous reviewers for their valued recommendations. The authors did not receive any kind of grant for this study to be carried out.  ... 
doi:10.5815/ijmecs.2020.05.04 fatcat:hbe5vzwumnfztcunjkv5pkbpvu

Evaluation of Hemodialysis Arteriovenous Bruit by Deep Learning

Keisuke Ota, Yousuke Nishiura, Saki Ishihara, Hihoko Adachi, Takehisa Yamamoto, Takayuki Hamano
2020 Sensors  
We also extracted arteriovenous fistula sounds for each heartbeat without environmental sound by using a convolutional neural network (CNN) model, which was made by comparing these sound patterns with  ...  The analysis of arteriovenous fistula sound using deep learning has the potential to be used as an objective index in daily medical care.  ...  Acknowledgments: The authors would like to thank the staff of Nagoya City University and Gamagori Municipal Hospital for their support and cooperation.  ... 
doi:10.3390/s20174852 pmid:32867220 pmcid:PMC7506665 fatcat:wl5mdqbajzeotckravegyxztwu

Intelligent IoT-Aided Early Sound Detection of Red Palm Weevils

Mohamed Esmail Karar, Omar Reyad, Abdel-Haleem Abdel-Aty, Saud Owyed, Mohd F. Hassan
2021 Computers Materials & Continua  
In this paper, we propose a new IoT-based framework for early sound detection of RPWs using fine-tuned transfer learning classifier, namely InceptionResNet-V2.  ...  Then, the acquired audio signals are sent to a cloud server for further on-line analysis by our fine-tuned deep transfer learning model, i.e., InceptionResNet-V2.  ...  Acknowledgement: The authors extend their appreciation to the Deputyship for Research & Innovation, Ministry of Education in Saudi Arabia for funding this research work through the project number (UB-26  ... 
doi:10.32604/cmc.2021.019059 fatcat:6s4t5ddcajagpedafi6d74wmcm

Sound Classification Using Convolutional Neural Network and Tensor Deep Stacking Network

Aditya Khamparia, Deepak Gupta, Nhu Gia Nguyen, Ashish Khanna, Babita Pandey, Prayag Tiwari
2019 IEEE Access  
Our aim, in this paper, is to use the deep learning networks for classifying the environmental sounds based on the generated spectrograms of these sounds.  ...  The learning capabilities of the deep learning architectures can be used to develop the sound classification systems to overcome efficiency issues of the traditional systems.  ...  [8] they proposed an integrated deep learning autoencoder based technique with extreme machine learning models which detects approaches that integrate extreme learning for detection of abstract signal  ... 
doi:10.1109/access.2018.2888882 fatcat:xsxjfow2qjdplhmrlbpf3m76a4

An Acoustic Events Recognition for Robotic Systems Based on a Deep Learning Method

Tadaaki Niwa, Takashi Kawakami, Ryosuke Ooe, Tamotsu Mitamura, Masahiro Kinoshita, Masaaki Wajima
2015 Journal of Computer and Communications  
In this paper, we provide a new approach to classify and recognize the acoustic events for multiple autonomous robots systems based on the deep learning mechanisms.  ...  As a new approach, trained deep learning networks which are constructed by RBMs, classify the acoustic events from input waveform signals.  ...  For example, a sound of environment that surrounds a living space is mixed a voice, a music, a engine sound of car, and a other living sound.  ... 
doi:10.4236/jcc.2015.311008 fatcat:5wjm5d2hf5hutjujqgodda6dz4

Hybrid Computerized Method for Environmental Sound Classification

Silvia Liberata Ullo, Smith K. Khare, Varun Bajaj, G. R. Sinha
2020 IEEE Access  
Lack of standardized methods for an automatic and effective environmental sound classification (ESC) creates a need to be urgently satisfied.  ...  The ESC-10, a ten-class environmental sound dataset, is used for the evaluation of the methodology.  ...  Thus, the proposed method proved to be promising and can be used to model a real-time environmental sound detection of natural sounds.  ... 
doi:10.1109/access.2020.3006082 fatcat:rlrn6l4xpfbctbjpfh4hgbklka

Research on Algorithm for Partial Discharge of High Voltage Switchgear Based on Speech Spectrum Features

Yueqin Feng, Quan Chen, Chunguang Li, Wenchao Hao
2017 Advances in Modelling and Analysis B  
Based on these, a mixed self-encoding deep learning network is constructed.  ...  The early methods based on ultrasonic detection have several shortcomings. For example, the equipment is expensive and the effective detection range is small.  ...  Consequently, the learned features can possess better recognition rates than the original features on the classifier. Deep learning is a semi-supervised learning method.  ... 
doi:10.18280/ama_b.600210 fatcat:yfzf7aozzfg4pej4q3ap6rw24a

Compact Bilinear Deep Features For Environmental Sound Recognition

Fatih Demir, Abdulkadir Sengur, Hao Lu, Shahin Amiriparian, Nicholas Cummins, Bjorn Schuller
2018 2018 International Conference on Artificial Intelligence and Data Processing (IDAP)  
Two publicly available environmental sound datasets are used to verify the efficacy of the approach namely, ESC-50 and ESC-10.  ...  Presented results indicate the suitability of the higher-order statistics of DEEP SPECTRUM representations for ESR classification tasks.  ...  CONCLUSION In this paper, we proposed a compact bilinear pooling method for environmental sound recognition (ESR).  ... 
doi:10.1109/idap.2018.8620779 fatcat:mypz32jr4na35kheylnnjdar2m

Unsupervised feature learning for bootleg detection using deep learning architectures

Michele Buccoli, Paolo Bestagini, Massimiliano Zanoni, Augusto Sarti, Stefano Tubaro
2014 2014 IEEE International Workshop on Information Forensics and Security (WIFS)  
We exploit a deep learning paradigm to extract highly characterizing features from audio excerpts, and a supervised classifier for detection.  ...  The method is validated against a dataset of nearly 500 songs, and results are compared to a state-of-the-art detector.  ...  Focusing on our problem, we make use of a deep learning network for unsupervised feature learning [14] .  ... 
doi:10.1109/wifs.2014.7084316 dblp:conf/wifs/BuccoliBZST14 fatcat:lwj2ggcmzbbrpdiuxkqwjqbnam

Multi-label vs. combined single-label sound event detection with deep neural networks

Emre Cakir, Toni Heittola, Heikki Huttunen, Tuomas Virtanen
2015 2015 23rd European Signal Processing Conference (EUSIPCO)  
In this paper, we compare two different deep learning methods for the detection of environmental sound events: combined single-label classification and multi-label classification.  ...  We investigate the accuracy of both methods on the audio with different levels of polyphony.  ...  Deep learning methods have recently given state-of-the-art results for many applications in environmental SED [2, 6] and speech recognition [7] .  ... 
doi:10.1109/eusipco.2015.7362845 dblp:conf/eusipco/CakirHHV15 fatcat:k5adiv27kfgnnjzkw22qdmexui

Automated identification of chicken distress vocalisations using deep learning models [article]

Axiu MAO, Claire Giraudet, Kai LIU, Ines De Almeida Nolasco, Zhiqin Xie, Zhixun Xie, Yue Gao, James Theobald, Devaki Bhatta, Rebecca Stewart, Alan G. McElligott
2021 bioRxiv   pre-print
Thus, a novel light-VGG11 was developed to automatically identify chicken distress calls using recordings (3,363 distress calls and 1,973 natural barn sounds) collected on intensive chicken farms.  ...  The light-VGG11 was modified from VGG11 with a significantly smaller size in parameters (9.3 million vs 128 million) and 55.88% faster detection speed while displaying comparable performance, i.e., precision  ...  We thank Michael Mcloughlin and Ben McCarthy for their help, and the farmers for access to their animals.  ... 
doi:10.1101/2021.12.15.472774 fatcat:rpghqpomqzbahp7leppqktm5da
« Previous Showing results 1 — 15 out of 36,735 results