2026-09-21T20:51:05Z https://www.ideals.illinois.edu/oai-pmh

oai:www.ideals.illinois.edu:2142/24283 2023-07-10 col_2142_5131 com_2142_5130

Hasegawa-Johnson, Mark A. Hasegawa-Johnson, Mark A. Sproat, Richard W. Shosted, Ryan K. Levinson, Stephen E. Lumetta, Steven S. Lim, Boon Pang 2011-05-25T14:52:30Z 2011-05-25T14:52:30Z 2011-05-25T14:52:30Z 2011-05 Whispering is a common type of speech which is not often studied in speech technology. Perceptual and physiological studies show us that whispered speech is subtly di erent from phonated speech, and is surprisingly able to carry a tremendous amount of information. In this dissertation we con- sider the question: What makes whispering a good form of communication? We examine the di erences between normal phonated speech and whispered speech, and gauge the e ectiveness of state-of-the-art speech recognition al- gorithms at recognizing whisper. Our perceptual experiments add to the literature on the intelligibility of whispered speech. Comparisons with ASR results yield interesting insights into the di erences between the two systems. A method for building speech recognizers for whispered speech using lim- ited whispered speech data is proposed and evaluated. Our approach ef- fectively performs speaker-adaptation for whispered speech acoustic models without needing whispered speech from the target speaker. Results show im- provement over the standard speaker-independent models. Our work opens up additional avenues for research, which are outlined in the conclusions. Item withdrawn by Mark Zulauf (zulauf@illinois.edu) on 2011-02-01T15:03:22Z Item was in collections: University of Illinois Theses & Dissertations (ID: 1) No. of bitstreams: 2 bplim_thesis_tex.tar.bz2: 113271 bytes, checksum: 8822ec3566330d2ce3a1dc4987c8cb4d (MD5) Lim_BoonPang.pdf: 3797403 bytes, checksum: 6b1379584dbbf0eb7596fd094861db0b (MD5) Made available in DSpace on 2011-05-25T14:52:30Z (GMT). No. of bitstreams: 3 Lim_BoonPang.pdf: 3797403 bytes, checksum: 6b1379584dbbf0eb7596fd094861db0b (MD5) license.txt: 4057 bytes, checksum: 170e0953c85a51530b3c517dcf36282d (MD5) bplim_thesis_tex.tar.bz2: 113271 bytes, checksum: 8822ec3566330d2ce3a1dc4987c8cb4d (MD5) http://hdl.handle.net/2142/24283 en (c) 2011 Boon Pang Lim speech recognition whispered speech modified rhyme test eigenvoices speaker adaptation Computational differences between whispered and non-whispered speech Electrical & Computer Eng 1933 Electrical & Computer Engr 1200 University of Illinois at Urbana-Champaign Dissertation Ph.D. PHD:Electr & Computer Eng-UIUC 10KS1200PHD