Acoustic scoring unit implemented on a single FPGA or ASIC
作者： Kai Yu , Rob A. Rutenbar
DOI:
关键词:
摘要: A hardware acoustic scoring unit for a speech recognition system and method of operation thereof are provided. Rather than all senones in an model used the system, logic first scores set ciphones based on features one frame sampled speech. The then associated with N highest scored ciphones. In embodiment, number (N) is three. While ciphones, high score ciphone identification operates parallel to identify or more additional that have greater threshold. Once finishes
google.co.uk 参考文章(89)
Octavian Cheng, Embedded speech recognition systems ResearchSpace@Auckland. ,(2008)
James M. O'reilly, Daryl Eigen, Modular system for accelerating data searches and data stream operations ,(1998)
Yasunaga Miyazawa, 康永 宮沢, Voice recognizing method and recording medium with recorded voice recognition processing program ,(2000)
Kim Dong Cheol, / Method and apparatus for providing text-to-speech and auto speech recognition on audio player ,(2002)
Cheong Fat Chan, Wei Han, A speech recognition ic with an efficient mfcc extraction algorithm and multi-mixture models The Chinese University of Hong Kong (People's Republic of China). ,(2006)
Edward C. Lin, Tsuhan Chen, Kai Yu, Robin A Rutenbar, Moving speech recognition from software to silicon: the in silico vox project. conference of the international speech communication association. pp. 2346- 2349 ,(2006)
Stephen Jonathan Melnikoff, Speech recognition in programmable logic University of Birmingham. ,(2003)
Rob A. Rutenbar, Patrick J. Bourke, A low-power hardware search architecture for speech recognition conference of the international speech communication association. pp. 2102- 2105 ,(2008)
Pierre Dumouchel, Gilles Boulianne, Patrick Cardinal, Michel Comeau, GPU accelerated acoustic likelihood computations. conference of the international speech communication association. pp. 964- 967 ,(2008)
Kai Yu, Robin A Rutenbar, Generating Small, Accurate Acoustic Models with a Modified Bayesian Information Criterion conference of the international speech communication association. pp. 2109- 2112 ,(2007)