Fujitsu Corporation

Chiharu Kawai

Hiroshi Katayama

Takehiro Nakai

Tomonori Sato

Tomohiko Taniguchi

Hideaki Kurihara

Yasushi Yamazaki

Hitoshi Matsuzawa

Rika Nishiike

The present invention provides an acoustic echo canceler for use in a telephone set having a handsfree conversation function. This acoustic echo canceler simultaneously achieves both the stabilization and speedup of an estimation operation and also attains the more improvement of speech quality. Moreover, the present invention provides a handsfree telephone set employing this acoustic echo canceler. Furthermore, this acoustic echo canceler is operative to cancel an echo generated by inputting an output of an acoustic device to itself substantially simultaneously with the outputting the output thereof. Further, this acoustic echo canceler comprises an adaptive filter for performing an operation of estimating the frequency characteristic and the phase characteristic of a part, whose frequency characteristic and phase characteristic vary, on an acoustic path and a fixed coefficient filter for simulating a part, whose frequency characteristic and phase characteristic are fixed, on the acoustic path.

Acoustic echo canceler and handsfree telephone set

A speech-recognizing apparatus for recognizing input speech comprises, an analysis unit for computing a characteristic vector for each of frames of the input speech, a correction-value storage unit for storing a correction distance in advance, a vector-to-vector-distance-computing unit for computing a vector-to-vector distance between the characteristic vector and the phoneme characteristic vector, an average-value-computing unit for computing an average value of vector-to-vector distances for one of the frames, a correction unit for computing a corrected vector-to-vector distance as a value of an expression of (the vector-to-vector distance-the average value&plus;the correction distance), and a recognition unit for cumulating corrected vector-to-vector distances into a cumulative vector-to-vector distance and comparing the cumulative vector-to-vector distance with the word standard pattern in order to recognize the input speech.

Speech recognizing apparatus

A device includes a plurality of DSPs, instruction memories respectively provided to the DSPs, a master memory storing download information which is to be written into the instruction memories, and an address generator generating addresses of the instruction memories and the master memories.

Device for simultaneously downloading code into plural DSP memories from single master memory

Speech processing coder, decoder and command recognizer

Growing community of inventors

Kawasaki, Japan

Chiharu Kawai