Matches in SemOpenAlex for { <https://semopenalex.org/work/W4330339902> ?p ?o ?g. }
Showing items 1 to 77 of
77
with 100 items per page.
- W4330339902 abstract "Social ambiance describes the context in which social interactions happen, and can be measured using speech audio by counting the number of concurrent speakers. This measurement has enabled various mental health tracking and human-centric IoT applications. While on-device Socal Ambiance Measure (SAM) is highly desirable to ensure user privacy and thus facilitate wide adoption of the aforementioned applications, the required computational complexity of state-of-the-art deep neural networks (DNNs) powered SAM solutions stands at odds with the often constrained resources on mobile devices. Furthermore, only limited labeled data is available or practical when it comes to SAM under clinical settings due to various privacy constraints and the required human effort, further challenging the achievable accuracy of on-device SAM solutions. To this end, we propose a dedicated neural architecture search framework for Energy-efficient and Real-time SAM (ERSAM). Specifically, our ERSAM framework can automatically search for DNNs that push forward the achievable accuracy vs. hardware efficiency frontier of mobile SAM solutions. For example, ERSAM-delivered DNNs only consume 40 mW x 12 h energy and 0.05 seconds processing latency for a 5 seconds audio segment on a Pixel 3 phone, while only achieving an error rate of 14.3% on a social ambiance dataset generated by LibriSpeech. We can expect that our ERSAM framework can pave the way for ubiquitous on-device SAM solutions which are in growing demand." @default.
- W4330339902 created "2023-03-22" @default.
- W4330339902 creator A5007488185 @default.
- W4330339902 creator A5019202280 @default.
- W4330339902 creator A5019319336 @default.
- W4330339902 creator A5065172226 @default.
- W4330339902 creator A5072109473 @default.
- W4330339902 creator A5077340762 @default.
- W4330339902 date "2023-03-19" @default.
- W4330339902 modified "2023-09-27" @default.
- W4330339902 title "ERSAM: Neural Architecture Search For Energy-Efficient and Real-Time Social Ambiance Measurement" @default.
- W4330339902 doi "https://doi.org/10.48550/arxiv.2303.10727" @default.
- W4330339902 hasPublicationYear "2023" @default.
- W4330339902 type Work @default.
- W4330339902 citedByCount "0" @default.
- W4330339902 crossrefType "posted-content" @default.
- W4330339902 hasAuthorship W4330339902A5007488185 @default.
- W4330339902 hasAuthorship W4330339902A5019202280 @default.
- W4330339902 hasAuthorship W4330339902A5019319336 @default.
- W4330339902 hasAuthorship W4330339902A5065172226 @default.
- W4330339902 hasAuthorship W4330339902A5072109473 @default.
- W4330339902 hasAuthorship W4330339902A5077340762 @default.
- W4330339902 hasBestOaLocation W43303399021 @default.
- W4330339902 hasConcept C119599485 @default.
- W4330339902 hasConcept C123657996 @default.
- W4330339902 hasConcept C127413603 @default.
- W4330339902 hasConcept C136764020 @default.
- W4330339902 hasConcept C138885662 @default.
- W4330339902 hasConcept C142362112 @default.
- W4330339902 hasConcept C151730666 @default.
- W4330339902 hasConcept C153349607 @default.
- W4330339902 hasConcept C186967261 @default.
- W4330339902 hasConcept C2742236 @default.
- W4330339902 hasConcept C2777421447 @default.
- W4330339902 hasConcept C2778707766 @default.
- W4330339902 hasConcept C2779343474 @default.
- W4330339902 hasConcept C41008148 @default.
- W4330339902 hasConcept C41895202 @default.
- W4330339902 hasConcept C76155785 @default.
- W4330339902 hasConcept C79403827 @default.
- W4330339902 hasConcept C82876162 @default.
- W4330339902 hasConcept C86803240 @default.
- W4330339902 hasConceptScore W4330339902C119599485 @default.
- W4330339902 hasConceptScore W4330339902C123657996 @default.
- W4330339902 hasConceptScore W4330339902C127413603 @default.
- W4330339902 hasConceptScore W4330339902C136764020 @default.
- W4330339902 hasConceptScore W4330339902C138885662 @default.
- W4330339902 hasConceptScore W4330339902C142362112 @default.
- W4330339902 hasConceptScore W4330339902C151730666 @default.
- W4330339902 hasConceptScore W4330339902C153349607 @default.
- W4330339902 hasConceptScore W4330339902C186967261 @default.
- W4330339902 hasConceptScore W4330339902C2742236 @default.
- W4330339902 hasConceptScore W4330339902C2777421447 @default.
- W4330339902 hasConceptScore W4330339902C2778707766 @default.
- W4330339902 hasConceptScore W4330339902C2779343474 @default.
- W4330339902 hasConceptScore W4330339902C41008148 @default.
- W4330339902 hasConceptScore W4330339902C41895202 @default.
- W4330339902 hasConceptScore W4330339902C76155785 @default.
- W4330339902 hasConceptScore W4330339902C79403827 @default.
- W4330339902 hasConceptScore W4330339902C82876162 @default.
- W4330339902 hasConceptScore W4330339902C86803240 @default.
- W4330339902 hasLocation W43303399021 @default.
- W4330339902 hasOpenAccess W4330339902 @default.
- W4330339902 hasPrimaryLocation W43303399021 @default.
- W4330339902 hasRelatedWork W1610545534 @default.
- W4330339902 hasRelatedWork W2017918794 @default.
- W4330339902 hasRelatedWork W2140725864 @default.
- W4330339902 hasRelatedWork W2293249214 @default.
- W4330339902 hasRelatedWork W4214556494 @default.
- W4330339902 hasRelatedWork W4223502243 @default.
- W4330339902 hasRelatedWork W4294751964 @default.
- W4330339902 hasRelatedWork W4294864783 @default.
- W4330339902 hasRelatedWork W574062871 @default.
- W4330339902 hasRelatedWork W2174684416 @default.
- W4330339902 isParatext "false" @default.
- W4330339902 isRetracted "false" @default.
- W4330339902 workType "article" @default.