-
公开(公告)号：DE69506037D1
公开(公告)日：1998-12-24
申请号：DE69506037
申请日：1995-06-15
Applicant: SONY CORP
Inventor： ASANO YASUHARU
Abstract: An audio output unit and method thereof for generating a natural and understandable composite tone as a whole. A fundamental frequency can greatly be reduced at a meaningful boundary of voice contents and a voice strictly reflecting a syntax structure can be outputted by changing the reduction characteristic of the phrase component of the fundamental frequency and thereby controlling the response characteristic of a secondary linear system to the phrase component to calculate the phrase component, so that it is possible to easily generate a natural and understandable composite tone as a whole.
-
公开(公告)号：DE60318990D1
公开(公告)日：2008-03-20
申请号：DE60318990
申请日：2003-03-05
Applicant: SONY CORP
Inventor： SHIMOMURA HIDEKI , AOYAMA KAZUMI , YAMADA KEIICHI , ASANO YASUHARU , OKUBO ATSUSHI
IPC: A63H11/00 , B25J5/00 , G05B19/04 , G06K9/00 , G06N3/00 , G06T7/00 , G10L13/00 , G10L15/00 , G10L15/06 , G10L15/20 , G10L15/22 , G10L15/26 , G10L15/28 , G10L17/00
Abstract: The learning apparatus acquires the name of an object by interacting with a person, and stores the acquired data by correlating with different feature data of the object, in a memory (65). A new object is recognized based on the stored data, and related information of the recognized object, are stored. Independent claims are also included for the following: (1) learning method; and (2) robot.
-
公开(公告)号：DE60014833T2
公开(公告)日：2005-11-17
申请号：DE60014833
申请日：2000-11-21
Applicant: SONY CORP
Inventor： ASANO YASUHARU , PAO HONGCHANG
Abstract: An voice synthesizing unit performs voice synthesizing processing, based on the state of emotion of a robot at an emotion/instinct model unit. For example, in the event that the emotion state of the robot represents "not angry", synthesized sound of "What is it?" is generated at the voice synthesizing unit. On the other hand, in the event that the emotion state of the robot represents "angry", synthesized sound of "Yeah, what?" is generated at the voice synthesizing unit, to express the anger. Thus, a robot with a high entertainment nature is provided.
-
公开(公告)号：DE60014833D1
公开(公告)日：2004-11-18
申请号：DE60014833
申请日：2000-11-21
Applicant: SONY CORP
Inventor： ASANO YASUHARU , PAO HONGCHANG
Abstract: An voice synthesizing unit performs voice synthesizing processing, based on the state of emotion of a robot at an emotion/instinct model unit. For example, in the event that the emotion state of the robot represents "not angry", synthesized sound of "What is it?" is generated at the voice synthesizing unit. On the other hand, in the event that the emotion state of the robot represents "angry", synthesized sound of "Yeah, what?" is generated at the voice synthesizing unit, to express the anger. Thus, a robot with a high entertainment nature is provided.
-
公开(公告)号：DE60318990T2
公开(公告)日：2009-02-05
申请号：DE60318990
申请日：2003-03-05
Applicant: SONY CORP
Inventor： SHIMOMURA HIDEKI , AOYAMA KAZUMI , YAMADA KEIICHI , ASANO YASUHARU , OKUBO ATSUSHI
IPC: A63H11/00 , B25J5/00 , G05B19/04 , G06K9/00 , G06N3/00 , G06T7/00 , G10L13/00 , G10L15/00 , G10L15/06 , G10L15/20 , G10L15/22 , G10L15/26 , G10L15/28 , G10L17/00
Abstract: The learning apparatus acquires the name of an object by interacting with a person, and stores the acquired data by correlating with different feature data of the object, in a memory (65). A new object is recognized based on the stored data, and related information of the recognized object, are stored. Independent claims are also included for the following: (1) learning method; and (2) robot.
-
Patent Agency Ranking
公开(公告)号：DE69625439T2
公开(公告)日：2003-10-02
申请号：DE69625439
申请日：1996-10-14
Applicant: SONY CORP
Inventor： ISHII KAZUO , YAMAMOTO EIJI , TANAKA MIYUKI , KAKUDA HIROSHI , ASANO YASUHARU , OGAWA HIROAKI , OMOTE MASANORI , MINAMINO KATSUKI
IPC: G09B29/10 , G01C21/00 , G01C21/36 , G08G1/0969 , G10L13/00 , G10L15/00 , G10L15/06 , G10L15/22 , G10L15/26 , G10L15/28 , G01C21/20
Abstract: Voice processing for recognizing a predetermined voice such as a place name, etc. is performed by a voice processing section 14 from an audio signal inputted from a microphone 11 on the basis of the operation of an operating means 18. When a map display, etc. based on the recognized place name, etc. are performed, an incorrect reading way and a place name tending to be mistaken can be also recognized. Accordingly, a high grade operation of a navigation apparatus can be simply performed without obstructing driving of a car, etc.
-
7.发明公开
公开(公告)号：EP0768638A3
公开(公告)日：1998-07-01
申请号：EP96307445
申请日：1996-10-14
Applicant: SONY CORP
Inventor： ISHII KAZUO , YAMAMOTO EIJI , TANAKA MIYUKI , KAKUDA HIROSHI , ASANO YASUHARU , OGAWA HIROAKI , OMOTE MASANORI , MINAMINO KATSUKI
IPC: G09B29/10 , G01C21/00 , G01C21/36 , G08G1/0969 , G10L13/00 , G10L15/00 , G10L15/06 , G10L15/22 , G10L15/26 , G10L15/28 , G10L3/00
CPC classification number: G01C21/3608 , G08G1/0969 , G10L15/26
Abstract: Voice processing for recognizing a predetermined voice such as a place name, etc. is performed by a voice processing section 14 from an audio signal inputted from a microphone 11 on the basis of the operation of an operating means 18. When a map display, etc. based on the recognized place name, etc. are performed, an incorrect reading way and a place name tending to be mistaken can be also recognized. Accordingly, a high grade operation of a navigation apparatus can be simply performed without obstructing driving of a car, etc.
Abstract translation: 用于识别一个预定话音语音处理：诸如地名等等是由语音处理部分14从来自麦克风11的操作的操作的基础上输入的音频信号执行手段18中。当一个地图显示等 基于所识别的地名等等进行，公认的不正确的阅读方式和地名趋向于被误认为是如此。 因此，外科手术导航装置的高品位的能够简单地进行不妨碍汽车的驾驶，等
-
公开(公告)号：EP1482480A4
公开(公告)日：2005-12-14
申请号：EP03710242
申请日：2003-03-05
Applicant: SONY CORP
Inventor： SHIMOMURA HIDEKI , AOYAMA KAZUMI , YAMADA KEIICHI , ASANO YASUHARU , OKUBO ATSUSHI
IPC: A63H11/00 , B25J5/00 , G05B19/04 , G06K9/00 , G06N3/00 , G06T7/00 , G10L13/00 , G10L15/00 , G10L15/06 , G10L15/20 , G10L15/22 , G10L15/26 , G10L15/28 , G10L17/00
CPC classification number: G06K9/00281 , G06N3/008 , G10L15/26
Abstract: A conventional robot apparatus or the like cannot learn a name in a natural way. A learning apparatus can acquire a name of an object through interaction with a human and stores it in correlation with a plurality of different feature data detected for the object. According to these data stored and information on correlation, the apparatus recognizes a new object, acquires a name and feature data of the new object (including a human), and stores information on correlation between them, thereby successively learning names of objects. A learning method and a robot apparatus are also disclosed.
-
-
公开(公告)号：DE60115738T2
公开(公告)日：2006-08-31
申请号：DE60115738
申请日：2001-02-26
Applicant: SONY CORP
Inventor： MINAMINO KATSUKI , ASANO YASUHARU , OGAWA HIROAKI , LUCKE HELMUT
Abstract: A preliminary word-selecting section selects one or more words following words which have been obtained in a word string serving as a candidate for a result of voice recognition; and a matching section calculates acoustic or linguistic scores for the selected words, and forms a word string serving as a candidate for a result of voice recognition according to the scores. A control section generates word-connection relationships between words in the word string serving as a candidate for a result of voice recognition, sends them to a word-connection-information storage section, and stores them in it. A re-evaluation section corrects the word-connection relationships stored in the word-connection-information storage section 16, and the control section determines a word string serving as the result of voice recognition according to the corrected word-connection relationships.
-
-
-
-
-
-
-
-
-
Search Results
22
records
(took 0.021 seconds)
