Matches in SemOpenAlex for { <https://semopenalex.org/work/W4385696593> ?p ?o ?g. }
Showing items 1 to 79 of
79
with 100 items per page.
- W4385696593 endingPage "12" @default.
- W4385696593 startingPage "1" @default.
- W4385696593 abstract "The environmental sound classification (ESC) has attracted increasing attention as the environmental sound contains a wealth of information that can be used to detect particular events. However, so far, most of the existing work in ESC still remains in the stage of algorithm design and the design of ESC processor has not been thoroughly investigated. The existing ESC processor designs have issues in meeting low power consumption and high accuracy simultaneously due to the lack of joint-optimization between algorithm and hardware, and very few work has demonstrated a complete ESC system containing all the necessary modules. In this work, a high accuracy and low power CNN-based ESC processor has been proposed, featuring: 1) a big-small CNN-based reconfigurable ESC processing hardware architecture to reduce the power consumption and hardware overhead while maintaining high classification accuracy. 2) a Mel feature adaptation engine reusing the neural network processing unit to further reduce the power consumption. 3) an event-driven ESC processing technique to reduce the inference time and the power consumption. The design has been implemented on a Kintex-7 FPGA and achieves low power consumption of 0.313W with high accuracy of 84.5% for the ESC-50 dataset, outperforming other state-of-the-art ESC processors." @default.
- W4385696593 created "2023-08-10" @default.
- W4385696593 creator A5006385656 @default.
- W4385696593 creator A5021327800 @default.
- W4385696593 creator A5027226262 @default.
- W4385696593 creator A5027989806 @default.
- W4385696593 creator A5038647640 @default.
- W4385696593 creator A5043336295 @default.
- W4385696593 creator A5053395445 @default.
- W4385696593 creator A5065150991 @default.
- W4385696593 creator A5082295616 @default.
- W4385696593 creator A5003081075 @default.
- W4385696593 date "2023-01-01" @default.
- W4385696593 modified "2023-09-27" @default.
- W4385696593 title "A High Accuracy and Low Power CNN-Based Environmental Sound Classification Processor" @default.
- W4385696593 doi "https://doi.org/10.1109/tcsi.2023.3299823" @default.
- W4385696593 hasPublicationYear "2023" @default.
- W4385696593 type Work @default.
- W4385696593 citedByCount "0" @default.
- W4385696593 crossrefType "journal-article" @default.
- W4385696593 hasAuthorship W4385696593A5003081075 @default.
- W4385696593 hasAuthorship W4385696593A5006385656 @default.
- W4385696593 hasAuthorship W4385696593A5021327800 @default.
- W4385696593 hasAuthorship W4385696593A5027226262 @default.
- W4385696593 hasAuthorship W4385696593A5027989806 @default.
- W4385696593 hasAuthorship W4385696593A5038647640 @default.
- W4385696593 hasAuthorship W4385696593A5043336295 @default.
- W4385696593 hasAuthorship W4385696593A5053395445 @default.
- W4385696593 hasAuthorship W4385696593A5065150991 @default.
- W4385696593 hasAuthorship W4385696593A5082295616 @default.
- W4385696593 hasConcept C107598950 @default.
- W4385696593 hasConcept C111919701 @default.
- W4385696593 hasConcept C121332964 @default.
- W4385696593 hasConcept C138885662 @default.
- W4385696593 hasConcept C149635348 @default.
- W4385696593 hasConcept C163258240 @default.
- W4385696593 hasConcept C2776401178 @default.
- W4385696593 hasConcept C2779960059 @default.
- W4385696593 hasConcept C2984118289 @default.
- W4385696593 hasConcept C41008148 @default.
- W4385696593 hasConcept C41895202 @default.
- W4385696593 hasConcept C42935608 @default.
- W4385696593 hasConcept C526435321 @default.
- W4385696593 hasConcept C62520636 @default.
- W4385696593 hasConcept C9390403 @default.
- W4385696593 hasConceptScore W4385696593C107598950 @default.
- W4385696593 hasConceptScore W4385696593C111919701 @default.
- W4385696593 hasConceptScore W4385696593C121332964 @default.
- W4385696593 hasConceptScore W4385696593C138885662 @default.
- W4385696593 hasConceptScore W4385696593C149635348 @default.
- W4385696593 hasConceptScore W4385696593C163258240 @default.
- W4385696593 hasConceptScore W4385696593C2776401178 @default.
- W4385696593 hasConceptScore W4385696593C2779960059 @default.
- W4385696593 hasConceptScore W4385696593C2984118289 @default.
- W4385696593 hasConceptScore W4385696593C41008148 @default.
- W4385696593 hasConceptScore W4385696593C41895202 @default.
- W4385696593 hasConceptScore W4385696593C42935608 @default.
- W4385696593 hasConceptScore W4385696593C526435321 @default.
- W4385696593 hasConceptScore W4385696593C62520636 @default.
- W4385696593 hasConceptScore W4385696593C9390403 @default.
- W4385696593 hasFunder F4320321001 @default.
- W4385696593 hasLocation W43856965931 @default.
- W4385696593 hasOpenAccess W4385696593 @default.
- W4385696593 hasPrimaryLocation W43856965931 @default.
- W4385696593 hasRelatedWork W1508811950 @default.
- W4385696593 hasRelatedWork W2282038838 @default.
- W4385696593 hasRelatedWork W2363175327 @default.
- W4385696593 hasRelatedWork W2368577056 @default.
- W4385696593 hasRelatedWork W2373066471 @default.
- W4385696593 hasRelatedWork W2566975275 @default.
- W4385696593 hasRelatedWork W2789718247 @default.
- W4385696593 hasRelatedWork W3094426418 @default.
- W4385696593 hasRelatedWork W3151483946 @default.
- W4385696593 hasRelatedWork W4366380722 @default.
- W4385696593 isParatext "false" @default.
- W4385696593 isRetracted "false" @default.
- W4385696593 workType "article" @default.