Resources Contact Us Home
Speech recognition device and speech recognition method

Image Number 5 for United States Patent #7272561.

Each word to be recognized is represented by gender-specific hidden Markov models that are stored in a ROM 6 along with output probability functions and preset transition probabilities. A speech recognizer 4 determines an occurrence probability of a feature parameter sequence detected by a feature value detector 3 using the hidden Markov models. The speech recognizer 4 determines the occurrence probability by giving each word a state sequence of one hidden Markov model common to the gender-specific hidden Markov models, multiplying each preset pair of an output probability function value and a transition probability together among the output probability functions and transition probabilities stored in the ROM 6, selecting the largest product as the probability of each state of the common hidden Markov model, determining the occurrence probability based on the selected product, and recognizing the input speech based on the occurrence probability thus determined.

  Recently Added Patents
Thin film switch and press key/keyboard using the same
Stain-blocking aqueous coating composition
Light-emitting diode devices
Femtocell one-to-many packet delivery
Apparatus and method for masking a clock signal
Inkjet ink
  Randomly Featured Patents
Toner supply device and toner cartridge
Methods and apparatus for providing video on demand and network PVR functions using IP streaming
Disk reproducing apparatus having active wide-range PLL device
Animal training device responsive to an audible signal
Circuit arrangement for operating an exhaust-gas probe
Adjustable sled module for mass storage devices
Portion of a multi-handled bag
Composition and method for treating penile erectile dysfunction
Process of making U.V. cured polyurethanes using diazonium salt promoters