TY  - THES
AB  - Oral communication is the most important way for delivering information in our daily life. Unfortu-nately, the quality of such communication can be degraded by 1) speech disorders (e.g. dysarthria) and 2) surrounding environments (e.g. noise or reverberation). Style conversion is a technology that modifies the source speaking style of a speaker to sound like a more intelligible target speak-ing style of either the same or different speaker. In the dissertation, I consider new machine learning based-approaches for style conversion. Inspired by the intelligibility gain of clear (CLR) speaking style over habitual (HAB) speaking style, I propose several HAB-to-CLR spectral mappings approaches for intelligibility improvement.
AU  - Dinh, Tuan A.
DA  - 2021
DO  - 10.6083/xk81jm08r
DO  - DOI
ID  - 9298
KW  - Dysarthria
KW  - Speech Intelligibility
KW  - Machine Learning
KW  - Parkinson Disease
KW  - computer neural networks
KW  - alaryngeal speech
L1  - https://digitalcollections.ohsu.edu/record/9298/files/Dinh.Tuan.2021.pdf
L2  - https://digitalcollections.ohsu.edu/record/9298/files/Dinh.Tuan.2021.pdf
L4  - https://digitalcollections.ohsu.edu/record/9298/files/Dinh.Tuan.2021.pdf
LK  - https://digitalcollections.ohsu.edu/record/9298/files/Dinh.Tuan.2021.pdf
N2  - Oral communication is the most important way for delivering information in our daily life. Unfortu-nately, the quality of such communication can be degraded by 1) speech disorders (e.g. dysarthria) and 2) surrounding environments (e.g. noise or reverberation). Style conversion is a technology that modifies the source speaking style of a speaker to sound like a more intelligible target speak-ing style of either the same or different speaker. In the dissertation, I consider new machine learning based-approaches for style conversion. Inspired by the intelligibility gain of clear (CLR) speaking style over habitual (HAB) speaking style, I propose several HAB-to-CLR spectral mappings approaches for intelligibility improvement.
PB  - Oregon Health and Science University
PY  - 2021
T1  - Improving speech intelligibility through spectral style conversion
TI  - Improving speech intelligibility through spectral style conversion
UR  - https://digitalcollections.ohsu.edu/record/9298/files/Dinh.Tuan.2021.pdf
Y1  - 2021
ER  -