Arslan, ÖzkanEngin, Erkan Zeki2022-05-112022-05-112018978-1538615010https://doi.org/10.1109/SIU.2018.8404344https://hdl.handle.net/20.500.11776/6440Aselsan;et al.;Huawei;IEEE Signal Processing Society;IEEE Turkey Section;Netas26th IEEE Signal Processing and Communications Applications Conference, SIU 2018 -- 2 May 2018 through 5 May 2018 -- -- 137780In this study, single-channel speech enhancement algorithms were evaluated with objective quality and objective intelligibility measures using Turkish speech database. The clean 30 sentences from the METU database are corrupted by car and babble noise types at -10, -5, 0, 5 and 10 dB SNR levels. The Karhunen-Loeve Transform has been found to be more successful than other methods in terms of both quality and intelligibility, given the amount of segmental SNR improvement, weighted spectral slope, short-time objective intelligibility values and spectrogram representations. © 2018 IEEE.tr10.1109/SIU.2018.8404344info:eu-repo/semantics/closedAccessObjective qualityShort-time objective intelligibilitySpeech enhancementMathematical transformationsPrincipal component analysisQuality controlSignal processingSignal to noise ratioSpeech intelligibilitySpeech recognitionBabble noiseKarhunen Loeve Transform (KLT)Objective qualitiesSingle-channel speech enhancement algorithmsSNR improvementSpectral slopesSpectrogramsSpeech databaseSpeech enhancementConference Object142-s2.0-85050796155