Publication: Towards ultra-low power consumption VAD architectures with mixed signal circuits
dc.affiliation.dpto | UC3M. Departamento de Tecnología Electrónica | es |
dc.affiliation.grupoinv | UC3M. Grupo de Investigación: Diseño Microelectrónico y Aplicaciones (DMA) | es |
dc.contributor.author | Shen, Yukai | |
dc.contributor.author | Straeussnigg, Dietmar | |
dc.contributor.author | Gutiérrez Fernández, Eric | |
dc.contributor.funder | European Commission | en |
dc.date.accessioned | 2023-08-22T07:15:14Z | |
dc.date.available | 2023-08-22T07:15:14Z | |
dc.date.issued | 2023 | |
dc.description | Proceedings of: 56th Edition IEEE ISCAS 2023 - IEEE International Symposium on Circuits and Systems (ISCAS), 21-25 May 2023, Monterey, CA, USA. | en |
dc.description.abstract | A voice activity detector architecture based on an analog feature extractor and a mixed signal classification stage is proposed for ultra-low power activity. The feature extraction stage is composed of a set of analog band-pass filters and frame energy estimators. The classification stage has a fully connected first layer built with ultra-low power consumption ring oscillators, followed by gated recurrent unit layers. The ring oscillator based layer consumes nWs according to transient simulations performed in a low power 65 nm CMOS technology. Additionally it features the ability to perform the analog-to-digital conversion required to handle subsequent GRU layers, as well as the possibility of computing a non-linear function like sigmoid seizing the intrinsic non-linearity of the ring oscillator. Training and testing operations are made proving competitive classification performance between a baseline model and our proposed architecture. In light of this, proper features for deployment on power-restricted edge-computing applications are shown. | en |
dc.description.sponsorship | This paper was supported by program H2020-MSCA-ITN-2020 grant Nr.956601. | en |
dc.format.extent | 5 | |
dc.identifier.bibliographicCitation | Shen, Y., Straeussnigg, D. & Gutierrez, E. (21-25 May 2023). Towards Ultra-Low Power Consumption VAD Architectures with Mixed Signal Circuits [proceedings]. 56th Edition IEEE ISCAS 2023: IEEE International Symposium on Circuits and Systems (ISCAS), Monterey, CA, USA. | en |
dc.identifier.doi | https://doi.org/10.1109/ISCAS46773.2023.10181669 | |
dc.identifier.issn | 2158-1525 | |
dc.identifier.publicationfirstpage | 1 | |
dc.identifier.publicationlastpage | 5 | |
dc.identifier.publicationtitle | Proceedings of 2023 IEEE International Symposium on Circuits and Systems (ISCAS) | en |
dc.identifier.uri | https://hdl.handle.net/10016/38065 | |
dc.identifier.uxxi | CC/0000034125 | |
dc.language.iso | eng | |
dc.publisher | IEEE | |
dc.relation.eventdate | 2023-05-21 | |
dc.relation.eventplace | ESTADOS UNIDOS DE AMERICA | es |
dc.relation.eventtitle | 56th Edition IEEE ISCAS 2023: IEEE International Symposium on Circuits and Systems (ISCAS) | en |
dc.relation.projectID | info:eu-repo/grantAgreement/EC/956601 | |
dc.rights | © 2023 IEEE. | es |
dc.rights.accessRights | open access | en |
dc.subject.eciencia | Educación | es |
dc.subject.eciencia | Electrónica | es |
dc.subject.eciencia | Telecomunicaciones | es |
dc.subject.other | Voice activity detection (VAD) | en |
dc.subject.other | Analog feature extraction | en |
dc.subject.other | Recurrent neural network (RNN) | en |
dc.subject.other | Gated recurrent unit (GRU) | en |
dc.subject.other | Ring oscillator (RO) | en |
dc.title | Towards ultra-low power consumption VAD architectures with mixed signal circuits | en |
dc.type | conference proceedings | * |
dc.type.hasVersion | AM | * |
dspace.entity.type | Publication |
Files
Original bundle
1 - 1 of 1
Loading...
- Name:
- Towards_ISCAS_2023_ps.pdf
- Size:
- 691.24 KB
- Format:
- Adobe Portable Document Format