Recognizing accented speech
作者： Kristin A. Gray
DOI:
关键词:
摘要: Techniques (300, 400, 500) and apparatuses (100, 200, 700) for recognizing accented speech are described. In some embodiments, an accent module recognizes (308) using library based on device data, uses different recognition correction levels application field into which recognized words set to be provided, or updates (310) corrections made incorrectly speech.
lens.org 参考文章(95)
Fang Lu, Janani Janakiraman, Susan M. Cox, Method to automatically enable closed captioning when a speaker has a heavy accent ,(2008)
Andrej Ljolje, Mazin Gilbert, System and method for improved automatic speech recognition performance ,(2009)
Sarah M. Banas, Sapient or Sentient Artificial Intelligence ,(2013)
Eric J. Horvitz, Marc Eliot Davis, Douglas C. Burger, Permissions Based on Behavioral Patterns ,(2011)
Tao Wang, Bin Zhou, Speech to text medical forms ,(2011)
John N. Nguyen, Michael S. Phillips, Speech recognition through the collection of contact information in mobile dictation application ,(2010)
Rudiger Gorny, Jurgen Rohner, Siegfried Anders, Wolfgang Nising, Marco Roelofs, Silke Kratschmer, Multi-layer product containing polycarbonate ,(2003)
Attila Muszta, Andreas Neubacher, Christina Drexel, Miklós Pápai, Herwig Häle, Latency Hiding Techniques for Multi-Modal User Interfaces ,(2011)
Emre M. Kiciman, Yi-Min Wang, Shuo Chen, Customizing Search Results ,(2008)
Nicholas Duffield, System and method for data intensive local inference ,(2010)