Matches in SemOpenAlex for { <https://semopenalex.org/work/W4220785590> ?p ?o ?g. }
- W4220785590 abstract "Deep neural speech and audio processing systems have a large number of trainable parameters, a relatively complex architecture, and require a vast amount of training data and computational power. These constraints make it more challenging to integrate such systems into embedded devices and utilize them for real-time, real-world applications. We tackle these limitations by introducing DeepSpectrumLite, an open-source, lightweight transfer learning framework for on-device speech and audio recognition using pre-trained image Convolutional Neural Networks (CNNs). The framework creates and augments Mel spectrogram plots on the fly from raw audio signals which are then used to finetune specific pre-trained CNNs for the target classification task. Subsequently, the whole pipeline can be run in real-time with a mean inference lag of 242.0 ms when a DenseNet121 model is used on a consumer-grade Motorola moto e7 plus smartphone. DeepSpectrumLite operates decentralized, eliminating the need for data upload for further processing. We demonstrate the suitability of the proposed transfer learning approach for embedded audio signal processing by obtaining state-of-the-art results on a set of paralinguistic and general audio tasks, including speech and music emotion recognition, social signal processing, COVID-19 cough and COVID-19 speech analysis, and snore sound classification. We provide an extensive command-line interface for users and developers which is comprehensively documented and publicly available at https://github.com/DeepSpectrum/DeepSpectrumLite." @default.
- W4220785590 created "2022-04-03" @default.
- W4220785590 creator A5010754413 @default.
- W4220785590 creator A5017889477 @default.
- W4220785590 creator A5043060302 @default.
- W4220785590 creator A5061806139 @default.
- W4220785590 creator A5079544804 @default.
- W4220785590 creator A5091269736 @default.
- W4220785590 date "2022-03-17" @default.
- W4220785590 modified "2023-10-14" @default.
- W4220785590 title "DeepSpectrumLite: A Power-Efficient Transfer Learning Framework for Embedded Speech and Audio Processing From Decentralized Data" @default.
- W4220785590 cites W131819148 @default.
- W4220785590 cites W2005374274 @default.
- W4220785590 cites W2065575936 @default.
- W4220785590 cites W2068026499 @default.
- W4220785590 cites W2090767179 @default.
- W4220785590 cites W2146334809 @default.
- W4220785590 cites W2294712740 @default.
- W4220785590 cites W2618530766 @default.
- W4220785590 cites W2790817016 @default.
- W4220785590 cites W2803193013 @default.
- W4220785590 cites W2884367402 @default.
- W4220785590 cites W2897132394 @default.
- W4220785590 cites W2912591385 @default.
- W4220785590 cites W2915760784 @default.
- W4220785590 cites W2947814289 @default.
- W4220785590 cites W2954996726 @default.
- W4220785590 cites W2964461714 @default.
- W4220785590 cites W2992308087 @default.
- W4220785590 cites W3097445517 @default.
- W4220785590 cites W3103802018 @default.
- W4220785590 cites W3109048247 @default.
- W4220785590 cites W3137890092 @default.
- W4220785590 cites W3173449808 @default.
- W4220785590 cites W3176923149 @default.
- W4220785590 cites W3196831814 @default.
- W4220785590 cites W4241677657 @default.
- W4220785590 doi "https://doi.org/10.3389/frai.2022.856232" @default.
- W4220785590 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/35372830" @default.
- W4220785590 hasPublicationYear "2022" @default.
- W4220785590 type Work @default.
- W4220785590 citedByCount "9" @default.
- W4220785590 countsByYear W42207855902022 @default.
- W4220785590 countsByYear W42207855902023 @default.
- W4220785590 crossrefType "journal-article" @default.
- W4220785590 hasAuthorship W4220785590A5010754413 @default.
- W4220785590 hasAuthorship W4220785590A5017889477 @default.
- W4220785590 hasAuthorship W4220785590A5043060302 @default.
- W4220785590 hasAuthorship W4220785590A5061806139 @default.
- W4220785590 hasAuthorship W4220785590A5079544804 @default.
- W4220785590 hasAuthorship W4220785590A5091269736 @default.
- W4220785590 hasBestOaLocation W42207855901 @default.
- W4220785590 hasConcept C108583219 @default.
- W4220785590 hasConcept C111919701 @default.
- W4220785590 hasConcept C127220857 @default.
- W4220785590 hasConcept C13895895 @default.
- W4220785590 hasConcept C150899416 @default.
- W4220785590 hasConcept C154945302 @default.
- W4220785590 hasConcept C157968479 @default.
- W4220785590 hasConcept C199360897 @default.
- W4220785590 hasConcept C204201278 @default.
- W4220785590 hasConcept C28490314 @default.
- W4220785590 hasConcept C41008148 @default.
- W4220785590 hasConcept C43521106 @default.
- W4220785590 hasConcept C45273575 @default.
- W4220785590 hasConcept C61328038 @default.
- W4220785590 hasConcept C64922751 @default.
- W4220785590 hasConcept C71901391 @default.
- W4220785590 hasConcept C81363708 @default.
- W4220785590 hasConceptScore W4220785590C108583219 @default.
- W4220785590 hasConceptScore W4220785590C111919701 @default.
- W4220785590 hasConceptScore W4220785590C127220857 @default.
- W4220785590 hasConceptScore W4220785590C13895895 @default.
- W4220785590 hasConceptScore W4220785590C150899416 @default.
- W4220785590 hasConceptScore W4220785590C154945302 @default.
- W4220785590 hasConceptScore W4220785590C157968479 @default.
- W4220785590 hasConceptScore W4220785590C199360897 @default.
- W4220785590 hasConceptScore W4220785590C204201278 @default.
- W4220785590 hasConceptScore W4220785590C28490314 @default.
- W4220785590 hasConceptScore W4220785590C41008148 @default.
- W4220785590 hasConceptScore W4220785590C43521106 @default.
- W4220785590 hasConceptScore W4220785590C45273575 @default.
- W4220785590 hasConceptScore W4220785590C61328038 @default.
- W4220785590 hasConceptScore W4220785590C64922751 @default.
- W4220785590 hasConceptScore W4220785590C71901391 @default.
- W4220785590 hasConceptScore W4220785590C81363708 @default.
- W4220785590 hasLocation W42207855901 @default.
- W4220785590 hasLocation W42207855902 @default.
- W4220785590 hasLocation W42207855903 @default.
- W4220785590 hasLocation W42207855904 @default.
- W4220785590 hasLocation W42207855905 @default.
- W4220785590 hasOpenAccess W4220785590 @default.
- W4220785590 hasPrimaryLocation W42207855901 @default.
- W4220785590 hasRelatedWork W1985168493 @default.
- W4220785590 hasRelatedWork W2338027094 @default.
- W4220785590 hasRelatedWork W2395878915 @default.
- W4220785590 hasRelatedWork W2736031499 @default.
- W4220785590 hasRelatedWork W2754746744 @default.
- W4220785590 hasRelatedWork W3007022793 @default.
- W4220785590 hasRelatedWork W4220785590 @default.