Environmental sound classification using a regularized deep convolutional neural network with data augmentation

CNN hyper-parameter optimization for environmental sound classification

In this paper we present the development of a patrol robot system for home security with some considerations on its interaction functionalities. The system integrates a variety of sensors to gather environmental information and detect abnormal events including fire alarm, intruder alert and lethal gas leakage. To facilitate a security robot to live with people in a home environment, we implement some dedicated human-robot interactions, including a face mask with several facial expressions and a force feedback steering wheel controller. All of the sensor measurements and the dedicated interactions can be remotely accessed via the Internet. We further design an indoor patrol algorithm that can autonomously command the mobile robot to move randomly, avoid obstacles, or steer along a wall baseline based on ultrasonic and vision data fusion. Finally, we apply the patrol robot system to patrol the second floor of EE building of our campus and provide several experimental results for validating its performance.

Development of a patrol robot for home security with network assisted interactions

Environmental Sound Classification (ESC) is a challenging field of research in non-speech audio processing. Most of current research in ESC focuses on designing deep models with special architectures tailored for specific audio datasets, which usually cannot exploit the intrinsic patterns in the data. However recent studies have surprisingly shown that transfer learning from models trained on ImageNet is a very effective technique in ESC. Herein, we propose SoundCLR, a supervised contrastive learning method for effective environment sound classification with state-of-the-art performance, which works by learning representations that disentangle the samples of each class from those of other classes. Our deep network models are trained by combining a contrastive loss that contributes to a better probability output by the classification layer with a cross-entropy loss on the output of the classifier layer to map the samples to their respective 1-hot encoded labels. Due to the comparatively small sizes of the available environmental sound datasets, we propose and exploit a transfer learning and strong data augmentation pipeline and apply the augmentations on both the sound signals and their log-mel spectrograms before inputting them to the model. Our experiments show that our masking based augmentation technique on the log-mel spectrograms can significantly improve the recognition performance. Our extensive benchmark experiments show that our hybrid deep network models trained with combined contrastive and cross-entropy loss achieved the state-of-the-art performance on three benchmark datasets ESC-10, ESC-50, and US8K with validation accuracies of 99.75\%, 93.4\%, and 86.49\% respectively. The ensemble version of our models also outperforms other top ensemble methods. The code is available at this https URL.

SoundCLR: Contrastive Learning of Representations For Improved Environmental Sound Classification.

Faculty of Engineering and Built Environment School of Electrical Engineering and Computer Science Doctor of Philosophy by Aaron Seng Wai Wong B Eng (Computer) & B Comp. Sci. (Hons. Class I) Companion robots are popular entities in the world of science fiction; however, in the real world no robot has been sufficiently programmed to act as a useful companion robot. There are still many issues to be resolved before this can be achieved, including the basic skills of walking, localisation and object recognition, and more difficult functions such as language, memory and human-robot interaction. Human emotions are shaped by cultural, genetic and environmental factors. Taking a wide-ranging approach to the context with respect to human-robot interactions, the surrounding environment has an effect on the way humans emotionally interact with each other. The focus of this is the extraction of environmental features (acoustic and visual) for use in human-robot interaction through an affective processing system on the robot. Applications of manifold learning were applied to acoustic and visual domains along with the design of an affective processing architecture.

Implementing sensory perception and affect on humanoid robots using applications of manifold learning

In this paper, we proposed a robot self position identification method by active sound localization. This method can be used for autonomous security robots working in room environments. A system using a AIBO robot equipped with two microphones and wireless network is constructed and is used for position identification experiments. Arrival time differences to the microphones of robot are used as localization cues. To overcome the ambiguity of front-back confusion, a three-head position measurement method was proposed. The robot position can be identified by the intersection of circles restricted by the azimuth differences to different speaker pairs. By localizing three or four speakers as sound beacons positioned on known locations, the robot can identify its self position with an average error of about 7 cm in a 2.5times3.0 m2 working space. A robot navigation experiment was conducted to demonstrate the effectiveness of the position identification system.

Robot navigation and sound based position identification

In this paper, we proposed a robot self position identification method by active sound localization. This method can be used for autonomous security robots working in room environments. A system using a AIBO robot equipped with two microphones and wireless network is constructed and is used for position identification experiments. Arrival time differences to the microphones of robot are used as localization cues. To overcome the ambiguity of front-back confusion, a three-head position measurement method was proposed. The robot position can be identified by the intersection of circles restricted by the azimuth differences to different speaker pairs. By localizing three or four speakers as sound beacons positioned on known locations, the robot can identify its self position with an average error of about 7 cm in a 2.5 times 3.0 m2 working space

Robot Position Identification by Actively Localizing Sound Beacons

Handle everyday research tasks with reliable, citation-backed results

Your personal Research Agent to handle research tasks with citation-backed results

Popular Tasks used by Researchers

How can I help with your research?

Meet SciSpace

Get more enhanced response by uploading the PDFs you want me to reference.

No relevant PDFs in your library

SciSpace is the AI research assistant for academics. Run systematic literature reviews on 280M+ papers, and write papers with cited sources. Trusted by 1M+ students, PhDs & researchers.

SciSpace | AI for Research

Analyze PDFs

Code & Manuscripts

Funding & Grants

Literature & Patents

Medical & Clinical Data

Systematic Review

Visualize & Present

Web & Data

Build a Google Scholar-like website for your research.

Build a website

Create charts and images for your research

Create a Chart

Write a paper for submission to a journal

Draft a manuscript

Patent Search

Design eye-catching scientific posters in minutes.

Scientific Poster Generation

Systematic Literature Review

One task is running at the moment. Your messages will be shown right after.

Drag and drop or click here to browse

Loved by <highlight>1 million+</highlight> researchers

Extract a list of specific topics and their sources from unstructured text

Topics

Compare and analyze relevant papers that matches with your search

Papers

Get insights from PDFs and bookmarked papers from your library

My library

Recent searches

Try searching for:

Catch AI-generated content in scholarly and non-scholarly content

{ai} Detector

Ai Writer

Get PDF Summaries, highlighted text explanations 

Chat with PDF

Effortlessly create in-text citations and bibliographies in APA and 2,500 other formats

Citation generator

Get explanations, summaries, and answers on academic papers

Ease up your research workflow with {scispace}'s cohort of exciting AI tools

Elevate your academic writing skills and convey your ideas the way you want

Paraphraser

Explore our range of reading and writing tools

Your file is being prepared and should be ready in a few minutes. If it's a large file, it might take a bit longer. You can close this window, and we'll email you the file when it's done.

You have reached a maximum limit of <strong>{limit}</strong> columns in the table. Remove at least <strong>1</strong> column to add or create another one.

M. Ebana

Author Tools

Chat about Author

Papers

Robot navigation and sound based position identification

Robot Position Identification by Actively Localizing Sound Beacons