Department of Computer Engineering2024-11-1020139781-4799-0356-61520-614910.1109/ICASSP.2013.66390292-s2.0-84890457569http://dx.doi.org/10.1109/ICASSP.2013.6639029https://hdl.handle.net/20.500.14288/17706We investigate spectral envelope mapping problem with joint analysis of throat- and acoustic-microphone recordings to enhance throatmicrophone speech. A new phone-dependent GMM-based spectral envelope mapping scheme, which performs the minimum mean square error (MMSE) estimation of the acoustic-microphone spectral envelope, has been proposed. Experimental evaluations are performed to compare the proposed mapping scheme to the state-of-theart GMM-based estimator using both objective and subjective evaluations. Objective evaluations are performed with the log-spectral distortion (LSD) and the wideband perceptual evaluation of speech quality (PESQ) metrics. Subjective evaluations are performed with the A/B pair comparison listening test. Both objective and subjective evaluations yield that the proposed phone-dependent mapping consistently improves performances over the state-of-the-art GMM estimator.AcousticsElectrical electronic engineeringEnhancement of throat microphone recordings by learning phone-dependent mappings of speech spectraConference proceedinghttps://www.scopus.com/inward/record.uri?eid=2-s2.0-84890457569&doi=10.1109%2fICASSP.2013.6639029&partnerID=40&md5=ac71746b68d6b7b1ca203f551dff89483296115070428603