- Acoustic Processing: features, modeling, training &
pronunciaion variation
½²©ú©É¡B¤ý·ç¼ý¡B¬x§Ó°¶
- Linguistin Processing & Language Modeling
ªL¨Î§»¡B³¯¬fµY¡B¼ï«³¸Û
- Search/Decoding Algorithm and Keyword Spotting
³¯¬fµY¡B¤ý«T¤¯¡B¼ï«³¸Û
- Robustness: noise/channel, features/modeling, hands-free
¬x§Ó°¶¡B¦¶°êµØ¡B¾G³ó¤å¡B³¯«a§Ê¡B¤ý·ç¼ý
- Speaker Adaptation & Recognition
³¯«a§Ê¡B¤ý·ç¼ý¡B¬x§Ó°¶¡B³¯«Û¹F¡B§d©Ó®Ì
- Spoken Dialogue and Speech/Language Understanding
¼ï«³¸Û¡B³¯¬fµY
- Speech-based Information Retrieval
¤ý«T¤¯¡B³¯¨Î¨j¡B³¯¬fµY
- Distributed Speech Recognition and Wireless Environments
§d©Ó®Ì¡B¦¶°êµØ
- Emerging Technologies
¾G³ó¤å
- Speech and Language Corpora
½²©ú©É¡B½²¸U¤è*¡B¤ý«T¤¯¡B³¯«Û¹F¡B§d©Ó®Ì
- Software Integration
³¯¬fµY¡B¼ï«³¸Û¡B¾G³ó¤å¡B¦ó»·¡B¤ý·ç¼ý¡B¦¶°êµØ
-
Text-o-Speech Systhesis
-
Dictation & Transcription
-
Multilingual Speech Recognition
-
Multimedia Technologies
-
Overall Pictures