Robust voice activity detection algorithm using spectrum estimation and dynamic thresholding

dc.date.accessioned2019-01-29T22:19:56Z
dc.date.accessioned2023-05-30T23:27:53Z
dc.date.available2019-01-29T22:19:56Z
dc.date.available2023-05-30T23:27:53Z
dc.date.created2019-01-29T22:19:56Z
dc.date.issued2009
dc.identifierurn:isbn:9781424443888
dc.identifierhttp://repositorio.ucsp.edu.pe/handle/UCSP/15904
dc.identifierhttps://doi.org/10.1109/LATINCOM.2009.5304908
dc.identifier.urihttps://repositorioslatinoamericanos.uchile.cl/handle/2250/6477716
dc.description.abstractAn algorithm for voice activity detection (VAD) is presented in this paper, it uses the classical short time fourier transform (STFT) followed by dynamic thresholding over the noise floor which allows accurate determination for voiced/unvoiced frame. This algorithm has also been implemented in a DSP plataform to evaluate its performance in real time, where results have shown that such method presents accurate voiced/unvoiced determination under unknown signal to noise ratio (SNR) conditions. © 2009 IEEE.
dc.languageeng
dc.publisherIEEE Computer Society
dc.relationhttps://www.scopus.com/inward/record.uri?eid=2-s2.0-70649084304&doi=10.1109%2fLATINCOM.2009.5304908&partnerID=40&md5=952276235657c495f3b7221b321fba89
dc.rightsinfo:eu-repo/semantics/restrictedAccess
dc.sourceRepositorio Institucional - UCSP
dc.sourceUniversidad Católica San Pablo
dc.sourceScopus
dc.subjectSignal detection
dc.subjectSpectrum analysis
dc.subjectSpeech recognition
dc.subjectDynamic thresholding
dc.subjectNoise floor
dc.subjectReal time
dc.subjectShort time Fourier transforms
dc.subjectSpectrum estimation
dc.subjectVoice activity detection
dc.subjectVoice activity detection algorithms
dc.subjectSignal to noise ratio
dc.titleRobust voice activity detection algorithm using spectrum estimation and dynamic thresholding
dc.typeinfo:eu-repo/semantics/conferenceObject


Este ítem pertenece a la siguiente institución