TY  - GEN
AB  - Continuous speech recognition systems are environmentally sensitive and suffer from the great variability of speech. In order to achieve recognition robustness, there's a strong interest among researchers on how to fuse different information sources for speech recognition. A common problem of those approaches is that complementary information is lost either before or after recognition.  To  avoid this unrecoverable information loss, and to better utilize this complementary information, we  proposed a run time information fbsion scheme.  The hypothesis of this thesis is that by  performing fusion at  different  levels and stages of a Large Vocabulary Continuous Speech Recognition  (LVCSR)  system,  especially inside the  decoder,  more reliable and efficient fusion is possible.
AD  - Oregon Health and Science University
AU  - Zheng, Chengyi
DA  - 2004-04-01
DO  - 10.6083/M4WH2N88
DO  - DOI
ED  - Yonghong, Yan
ED  - Advisor
ID  - 2357
KW  - Speech Perception
KW  - Speech Recognition Software
L1  - https://digitalcollections.ohsu.edu/record/2357/files/3089_etd.pdf
L2  - https://digitalcollections.ohsu.edu/record/2357/files/3089_etd.pdf
L4  - https://digitalcollections.ohsu.edu/record/2357/files/3089_etd.pdf
LK  - https://digitalcollections.ohsu.edu/record/2357/files/3089_etd.pdf
N2  - Continuous speech recognition systems are environmentally sensitive and suffer from the great variability of speech. In order to achieve recognition robustness, there's a strong interest among researchers on how to fuse different information sources for speech recognition. A common problem of those approaches is that complementary information is lost either before or after recognition.  To  avoid this unrecoverable information loss, and to better utilize this complementary information, we  proposed a run time information fbsion scheme.  The hypothesis of this thesis is that by  performing fusion at  different  levels and stages of a Large Vocabulary Continuous Speech Recognition  (LVCSR)  system,  especially inside the  decoder,  more reliable and efficient fusion is possible.
PB  - Oregon Health and Sciences University
PY  - 2004-04-01
T1  - Run-time information fusion in large vocabulary continuous speech recognition
TI  - Run-time information fusion in large vocabulary continuous speech recognition
UR  - https://digitalcollections.ohsu.edu/record/2357/files/3089_etd.pdf
Y1  - 2004-04-01
ER  -