Method and apparatus for speech recognition and reproduction
作者： Stephen P. Gill
DOI: 10.1121/1.396797
关键词: Amplitude 、 Computer science 、 Arithmetic mean 、 Data reduction 、 Spectral analysis 、 Pattern recognition 、 Communication channel 、 Reduction (complexity) 、 Artificial intelligence 、 Feature (machine learning) 、 Signal processing
摘要: Speech signal analysis for data reduction, as stored synthesis or recognition, is improved by features including: digital spectral analysis; reduction of channel and bit allocation selective summation groups contiguous data; using the mean average log amplitude to find deviation each channel; also instaneous shape value pairs adjacent frames, all combined a feature ensemble pair frames.
scitation.org
harvard.edu
aip.org
google.co.in 参考文章(6)
James Loton Flanagan, Phase vocoder speech synthesis system ,(1974)
Michel Cartier, Pierre Lorand, Gilbert Marie Marcel Ferrieu, Guy Albert Jules David, Vocoder system using delta modulation ,(1974)
Frank C. Pirz, Lawrence R. Rabiner, Multiple template speech recognition system ,(1979)
Robert F Owens, Myron H Hitchcock, Warren L Holford, Method and apparatus for interpretation of time-varying signals ,(1969)
Hinrichs, Ove, Dipl.-Ing., Berlin, Gonschorek, Joerg, Dipl.-Ing., Gifhorn, Speech recognition analyser circuit - has multichannel filters operating into comparators to provide sampled values for memory ,(1979)