Method and system for automatic speech recognition
作者： Feng Rao , Shuai Yue , Bo Chen , Li Lu , Xiang Zhang
DOI:
关键词: Node (networking) 、 Pattern recognition 、 Token passing 、 String (computer science) 、 Speech recognition 、 Artificial intelligence 、 Decoding methods 、 Security token 、 Speech input 、 Computer science
摘要: A method and system for automatic speech recognition is provided. The includes generating a decoding network that primary sub-network classification sub-network. node corresponding to the corresponds group of uncommon words. Speech input received decoded by instantiating token in passing through network. When reaches node, transferring an accept sub-network, returning result one or more words string output
google.com.au 参考文章(67)
Kristie Seymore, Ronald Rosenfeld, Large-Scale Topic Detection and Language Model Adaptation. Defense Technical Information Center. ,(1997) , 10.21236/ADA327553
Francoise Beaufays, Hasim Sak, Speech transcription including written text ,(2013)
Daisuke Tomoda, Yoshinori Tahara, Hiroaki Kashima, Statistical language model generating device, speech recognizing device, statistical language model generating method, speech recognizing method, and program ,(2004)
Roland Kuhn, George Foster, Means and Method for Adapted Language Translation ,(2006)
Li Deng, Dong Yu, Alejandro Acero, Xiaolong Li, Time synchronous decoding for long-span hidden trajectory model ,(2006)
Alejandro Acero, Yik-Cheung Tam, Milind Mahajan, Ciprian Chelba, Language model adaptation using semantic supervision ,(2004)
Brandon M. Ballinger, Michael H. Cohen, Johan Schalkwyk, Cyril Georges Luc Allauzen, Language Model Selection for Speech-to-Text Conversion ,(2010)
Nicola Cancedda, Viet Ha-Thuc, Method and system for confidence-weighted learning of factored discriminative language models ,(2011)
Benyu Zhang, HuaJun Zeng, Zheng Chen, Jian Wang, Jilin Chen, Diverse topic phrase extraction ,(2007)
Carl Joseph Kraenzel, Baiju Dhirajlal Mandalia, David M. Lubensky, Dialog filtering for filling out a form ,(2008)