About: Emotional sounds of crowds: spectrogram-based analysis using deep learning

Facets (new session)
Description
Metadata
Settings
- owl:sameAs
- Inference Rule:

About: Emotional sounds of crowds: spectrogram-based analysis using deep learning Goto Sponge NotDistinct Permalink

An Entity of Type : schema:ScholarlyArticle, within Data Space : covidontheweb.inria.fr associated with source document(s)

Attributes	Values
type	Academic Article research paper schema:ScholarlyArticle
isDefinedBy	Covid-on-the-Web dataset
has title	Emotional sounds of crowds: spectrogram-based analysis using deep learning
Creator	Biondi, Giulio Franzoni, Valentina Milani, Alfredo
Source	Medline; PMC
abstract	Crowds express emotions as a collective individual, which is evident from the sounds that a crowd produces in particular events, e.g., collective booing, laughing or cheering in sports matches, movies, theaters, concerts, political demonstrations, and riots. A critical question concerning the innovative concept of crowd emotions is whether the emotional content of crowd sounds can be characterized by frequency-amplitude features, using analysis techniques similar to those applied on individual voices, where deep learning classification is applied to spectrogram images derived by sound transformations. In this work, we present a technique based on the generation of sound spectrograms from fragments of fixed length, extracted from original audio clips recorded in high-attendance events, where the crowd acts as a collective individual. Transfer learning techniques are used on a convolutional neural network, pre-trained on low-level features using the well-known ImageNet extensive dataset of visual knowledge. The original sound clips are filtered and normalized in amplitude for a correct spectrogram generation, on which we fine-tune the domain-specific features. Experiments held on the finally trained Convolutional Neural Network show promising performances of the proposed model to classify the emotions of the crowd.
has issue date	2020-08-17(xsd:dateTime)
bibo:doi	10.1007/s11042-020-09428-x
bibo:pmid	32837250
has license	cc-by
sha1sum (hex)	9c1ef27ba697b011474511a742705519ca72a7b3
schema:url	https://doi.org/10.1007/s11042-020-09428-x
resource representing a document's title	Emotional sounds of crowds: spectrogram-based analysis using deep learning
has PubMed Central identifier	PMC7429201
has PubMed identifier	32837250
schema:publication	Multimed Tools Appl
resource representing a document's body	covid:9c1ef27ba697b011474511a742705519ca72a7b3#body_text
is schema:about of	named entity 'matches' named entity 'cheering' named entity 'theaters' named entity 'WHERE' named entity 'GENERATION' named entity 'COLLECTIVE' named entity 'LENGTH' named entity 'TECHNIQUES' named entity 'CHARACTERIZED' named entity 'individual' named entity 'emotional' named entity 'individual' named entity 'extracted' named entity 'amplitude' named entity 'Convolutional Neural Network' named entity 'generation' named entity 'filtered' named entity 'political demonstrations' named entity 'sounds' named entity 'features' named entity 'emotion' named entity 'training set' named entity 'experimental settings' named entity 'learning rate' named entity 'CNN' named entity 'training set' named entity 'psychophysical' named entity 'collective behavior' named entity 'overfitting' named entity 'shopping mall' named entity 'Mel scale' named entity 'Creative Commons Attribution 4.0' named entity 'audio dubbing' named entity 'spectrogram' named entity 'spectrogram' named entity 'emotion' named entity 'sound produced' named entity 'cognitive knowledge' named entity 'deep-learning' named entity 'general idea' named entity 'spectrogram' named entity 'spectrogram' named entity 'spectrogram' named entity 'CNN' named entity 'spectrogram' named entity 'emotion recognition' named entity 'random sample' named entity 'Cybernetics' named entity 'spectrogram' named entity 'Web' named entity 'emotion recognition' named entity 'emotion' named entity 'Transfer Learning' named entity 'Knowledge Transfer' named entity 'human speech' named entity 'emotion recognition' named entity 'ImageNet' named entity 'CNN' named entity 'Transfer Learning' named entity 'training set' named entity 'delusion' named entity 'Mel scale' named entity 'spectrogram' named entity 'ImageNet' named entity 'image classification' named entity 'training set' named entity 'copyright holder' named entity 'human voice' named entity 'IEEE' named entity 'speech recognition' named entity 'emotion' named entity 'neural network' named entity 'Loudness' named entity 'algorithm' named entity 'Spectrogram' named entity 'EBU R128' named entity 'transfer learning' named entity 'Creative Commons licence' named entity 'Bark scale'

Faceted Search & Find service v1.13.91 as of Mar 24 2020

Alternative Linked Data Documents: Sponger | ODE Content Formats:

RDF

ODATA

Microdata

About

OpenLink Virtuoso version 07.20.3229 as of Jul 10 2020, on Linux (x86_64-pc-linux-gnu), Single-Server Edition (94 GB total memory)
Data on this page belongs to its respective rights holders.
Virtuoso Faceted Browser Copyright © 2009-2024 OpenLink Software