2026-03-10T15:14:13Z https://repository.lib.tottori-u.ac.jp/oai

oai:repository.lib.tottori-u.ac.jp:00007216 2023-09-29T00:39:46Z 1:10 2:12

Speech Enhancement Based on Frequency Domain ALE with Adaptive De-Correlation Parameters 80243377 Nakanishi, Isao Nakanishi, Isao Namba, Hironori Li, Shigang Namba, Hironori Li, Shigang copyright©2013 Inderscience / Under a Creative Commons license: CC BY-NC-ND 4.0 Adaptive line enhancer de-correlation parameter frequency domain speech enhancement Adaptive line enhancer de-correlation parameter frequency domain speech enhancement We have proposed the speech enhancement method using the frequency domain adaptive line enhancer, which enables to independently set de-correlation parameters at frequency bins. In the conventional method, we divided the frequency band into four domains and set a de-correlation parameter at each domain. However, the spectral distribution of voices varies depending on gender and/or age differences. In this paper, we propose to adaptively control the de-correlation parameter according to the signal-to-noise ratio at each domain. Moreover, we propose to adjust the frequency width of each domain to a detected pitch (fundamental frequency). Their effectiveness is evaluated in simulations. International Association of Computer Science and Information Technology Press (IACSIT Press) 2013-04-01 eng journal article VoR https://repository.lib.tottori-u.ac.jp/records/7216 10.7763/IJCTE.2013.V5.696 International Journal of Computer Theory and Engineering. 2013, 5(2), 292-297 http://www.ijcte.org/ http://www.ijcte.org/ 17938201 International Journal of Computer Theory and Engineering International Journal of Computer Theory and Engineering 5 2 292 297 https://repository.lib.tottori-u.ac.jp/record/7216/files/ijct5(2)_292.pdf application/pdf 1.6 MB 2018-05-11