DC Field | Value | Language |
---|---|---|
dc.contributor.author | 윤성욱 | - |
dc.date.accessioned | 2022-03-29T03:53:15Z | - |
dc.date.available | 2022-03-29T03:53:15Z | - |
dc.date.issued | 2022 | - |
dc.identifier.other | OAK-2015-09456 | - |
dc.identifier.uri | http://postech.dcollection.net/common/orgView/200000598094 | ko_KR |
dc.identifier.uri | https://oasis.postech.ac.kr/handle/2014.oak/112261 | - |
dc.description | Master | - |
dc.description.abstract | Keyword Spotting (KWS) is a task that detects wake-up words or distinguishes commands in a stream of audio. Since this type of task is normally used on low-resource devices, such a task requires an implementation that has a small memory footprint and low power usage. In this thesis, temporal blueprint separable convolutions are presented as highly efficient blocks that can be incorporated into Convolutional Neural Networks (CNNs) used for KWS. Based on intra-kernel correlation properties from trained CNN models, temporal blueprint separable convolutions are shown to more efficiently separate regular temporal convolutions than temporal depthwise separable convolutions. In addition to temporal blueprint separable convolutions, group convolutions with channel shuffle and a Multi-Scale Temporal Blueprint (MTB) method is used in the proposed approach. It is experimentally shown that the proposed KWS models achieve high accuracy with a small footprint. | - |
dc.language | eng | - |
dc.publisher | 포항공과대학교 | - |
dc.title | Temporal Blueprint Separable Convolution for Efficient Keyword Spotting | - |
dc.title.alternative | 효율적인 키워드 스팟팅을 위한 시계열 청사진 분리 합성곱 | - |
dc.type | Thesis | - |
dc.contributor.college | 일반대학원 전자전기공학과 | - |
dc.date.degree | 2022- 2 | - |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.
library@postech.ac.kr Tel: 054-279-2548
Copyrights © by 2017 Pohang University of Science ad Technology All right reserved.