-
公开(公告)号:JP2001215993A
公开(公告)日:2001-08-10
申请号:JP2000022225
申请日:2000-01-31
Applicant: SONY CORP
Inventor: ASANO KOJI , AOYANAGI SEIICHI , TANAKA MIYUKI , YOKONO JUN , OE TOSHIO
Abstract: PROBLEM TO BE SOLVED: To conduct interactive operations having rich variations depending on the feeling condition of a user. SOLUTION: In a voice recognition section 2, user's voice is recognized and phoneme information of the voice is extracted. In an interactive control section 3, conceptual information of the words and the phrases included in the voice recognition result obtained by the section 2 is extracted. An image inputting section 6 photographs the face of the user and outputs face image information. In a physiological information inputting section 7, physiological information such as the pulse rate of the user is detected. Then, a user feeling information updating section 8 estimates the feeling of the user based on the phoneme, the conceptual, the face image and the physiological information. In the section 3 and a sentence generating section 4, an output sentence is generated and outputted to the user based on the estimated result of the feeling.
-
公开(公告)号:JP2001188788A
公开(公告)日:2001-07-10
申请号:JP37577199
申请日:1999-12-28
Applicant: SONY CORP
Inventor: AOYANAGI SEIICHI , ASANO KOJI , TANAKA MIYUKI , YOKONO JUN , OE TOSHIO
IPC: G10L13/00 , G06F9/44 , G06F17/00 , G06F17/28 , G06F19/00 , G06N5/04 , G10L13/04 , G10L13/08 , G10L15/00 , G10L15/22
Abstract: PROBLEM TO BE SOLVED: To supply corresponding conversation rich in variety to a user. SOLUTION: Information inputted to a language information inputting part 41 with the voice of a user or the like is language processed by a language processing part 42. An interactive managing part 43 prepares data being the origin of an interactive sentence based on the processed result from the language processing part 42 and a parameter stored in a parameter storing part 44, and output it to a response generating part 45. The response generating part 45 generates and utters a response sentence according to data from the interactive managing part 43 or the instruction of a reaction generating part 47. The parameter stored in the parameter storing part 44 is dynamically updated according to various conditions by a parameter updating part 46.
-
公开(公告)号:JP2001209662A
公开(公告)日:2001-08-03
申请号:JP2000015265
申请日:2000-01-25
Applicant: SONY CORP
Inventor: AOYANAGI SEIICHI , ASANO KOJI , TANAKA MIYUKI , YOKONO JUN , OE TOSHIO
Abstract: PROBLEM TO BE SOLVED: To easily collect user information on the hobby, taste or the like of a user. SOLUTION: The speech of the user is recognized in a speech recognition part 1 and a dialogue sentence dialoguing with the user is generated based on the speech recognized result and outputted in a language processing part 2, a dialogue management part 3 and a response generation part 5. Further, in the dialogue management part 3, the user information on the hobby, taste or the like of the user is collected based on the speech recognized result.
-
公开(公告)号:JP2001209644A
公开(公告)日:2001-08-03
申请号:JP2000020320
申请日:2000-01-28
Applicant: SONY CORP
Inventor: YOKONO JUN , ASANO KOJI , AOYANAGI SEIICHI , TANAKA MIYUKI , OE TOSHIO
Abstract: PROBLEM TO BE SOLVED: To easily provide the message of an expression appropriate for an opposite party. SOLUTION: The speech of a user is voice-recognized in a voice recognition part 1, language-processed in a language processing part 2 and then supplied to an intention understanding part 3. In the intention understanding part 3, the opposite party to transmit the message and contents desired to be transmitted are recognized. In a sentence generation part 6, based on the recognized result, the message of the contents desired to be transmitted by the expression corresponding to intimacy with the opposite party to transmit the message is generated.
-
公开(公告)号:JPH10312597A
公开(公告)日:1998-11-24
申请号:JP11966497
申请日:1997-05-09
Applicant: SONY CORP
Inventor: FUJITA GORO , OE TOSHIO
IPC: G11B11/10 , G11B7/00 , G11B7/005 , G11B11/105
Abstract: PROBLEM TO BE SOLVED: To extract a reproduction signal corresponding to a mark with high accuracy by preventing a pulse signal synchronized with a data clock signal from being superposed on the driving signal of a recording/reproducing light source for an interval where a mark having phase information is preformatted at the time of data recording. SOLUTION: At the time of writing a data, a record data Dr is fed to a magnetic head driver 16 and a magnetic head 15 generates a corresponding magnetic field for recording the record data Dr in the data region of a magnetooptic disc 11 in conjunction with a laser beam from an optical head 17. A laser driver 18 is normally fed with a data clock signal DCK from a data clock reproducer and a laser beam modulated by the record data Dr is further modulated by the data clock signal DCK. A system controller 51 interrupts data clock signal DCK supply to the laser driver 18 only during an interval where a clock mark us preformatted.
-
公开(公告)号:JP2001188668A
公开(公告)日:2001-07-10
申请号:JP37577299
申请日:1999-12-28
Applicant: SONY CORP
Inventor: ASANO KOJI , AOYANAGI SEIICHI , TANAKA MIYUKI , YOKONO JUN , OE TOSHIO
Abstract: PROBLEM TO BE SOLVED: To control an equipment connected to a network by voice. SOLUTION: A user utters about desired operation to the microphone 11 of a voice dialog device 1 when the equipment connected to the network is operated. Inputted utterance by the user is recognized by a voice recognizing part 12. A dialog processing part 13 generates information to enable operation according to a recognition result. The generated information is outputted to a communicating part 17 and further transmitted to the equipment defined as an operating object via the network. The equipment executes a processing according to the information transmitted via the network.
-
公开(公告)号:JP2000322077A
公开(公告)日:2000-11-24
申请号:JP13164899
申请日:1999-05-12
Applicant: SONY CORP
Inventor: IWASE SUMIO , NAGUMO FUMIO , OE TOSHIO
IPC: G06F17/28 , G10L11/02 , G10L13/00 , G10L13/08 , G10L15/00 , G10L15/04 , G10L15/22 , G10L15/24 , H04N5/445
Abstract: PROBLEM TO BE SOLVED: To favorably display subtitles and perform dubbing in a random language. SOLUTION: A signal from antennas 1 and 2 is supplied to a demultiplexer 4 through a front-end circuit 3 and a separated picture signal is supplied to a standard system encoder 11 through an image decoder 6, a synchronization information writing circuit 8, a delay circuit 9 and a mixer 10. A speech signal separated at the demultiplexer 4 is supplied to a text conversion circuit 14 through a speech decoder 7 and the text converted data is supplied to the mixer 10 through a display signal generating circuit 15 and a synchronous filter 16. A spectrum pattern of a speech extracted from the text conversion circuit 14 is supplied to a spectrum analyzing circuit 17 and a mouth image of the picture signal from the decoder 6 is supplied to an image recognition circuit 18 for detecting a point of time where speakers change. These detected signals are supplied to the display signal generating circuit 15 through a vocal time judging circuit 19 and a display time is controlled.
-
-
-
-
-
-