专利快速检索-快速检索全球专利，免费商用专利数据库-IPRDB

81. 发明专利

JPS59168499A Pattern recognition system 失效
标题翻译：模式识别系统
公开(公告)号：JPS59168499A
公开(公告)日：1984-09-22
申请号：JP4217283
申请日：1983-03-16
申请人： Hitachi Ltd
发明人： ASAKAWA YOSHIAKI , KOMATSU AKIO , HATAOKA NOBUO , ICHIKAWA AKIRA , UMEMURA KAZUHIRO
IPC分类号： G10L11/00 , G06K9/62 , G10L15/12

82. 发明专利

JPS5979295A Preparation of voice standard pattern 失效
公开(公告)号：JPS5979295A
公开(公告)日：1984-05-08
申请号：JP18904482
申请日：1982-10-29
申请人： Hitachi Ltd
发明人： HATAOKA NOBUO , ICHIKAWA AKIRA
IPC分类号： G10L11/00 , G10L15/06

83. 发明专利

JPS58189694A Voice recognition system 失效
公开(公告)号：JPS58189694A
公开(公告)日：1983-11-05
申请号：JP7122582
申请日：1982-04-30
申请人： Hitachi Ltd
发明人： ICHIKAWA AKIRA , HATAOKA NOBUO , KIMURA TOSHIHIRO
IPC分类号： G10L11/00 , G10L15/06 , G10L15/10 , G10L15/28

84. 发明专利

JPS57204094A PRETREATMENT FOR VOICE ANALYZER 失效
公开(公告)号：JPS57204094A
公开(公告)日：1982-12-14
申请号：JP8815281
申请日：1981-06-10
申请人： HITACHI LTD
发明人： HATAOKA NOBUO
IPC分类号： G10L15/20 , G10L11/00 , G10L11/02 , G10L15/02 , G10L15/04 , G10L19/00 , G10L21/02 , H03H17/00 , H03H17/02 , H03H17/04 , H03H21/00

85. 发明专利

JP2006251061A Voice dialog apparatus and voice dialog method 审中-公开
标题翻译：语音对话设备和语音对话方法
公开(公告)号：JP2006251061A
公开(公告)日：2006-09-21
申请号：JP2005064227
申请日：2005-03-08
申请人： Hitachi Ltd , Nissan Motor Co Ltd , Xanavi Informatics Corp , 日産自動車株式会社 , 株式会社ザナヴィ・インフォマティクス , 株式会社日立製作所
发明人： ONO TAKESHI , TOGASHI MINORU , TOMOTA TAKAHISA , HATAOKA NOBUO , KUJIRAI TOSHIHIRO
IPC分类号： G10L15/28 , G10L15/22
摘要： PROBLEM TO BE SOLVED: To provide a voice dialog apparatus for suppressing the occurrence of erroneous recognition by enabling a user to intuitively comprehend to what degree the user may change an utterance method, and also to provide a voice dialog method.
SOLUTION: The voice dialog system recognizes utterance of the user by voice recognition means (11 and 14), analyzes the utterance of the user by an utterance analysis means (14), predicts erroneous recognition factors contributed to erroneous recognition on the basis of an analysis result by the utterance analysis means, and voice-synthesizes responses including a recognition result of the user by responding means (12 and 14) to be output. The responding means responds by performing utterance conversion emphasizing the erroneous recognition factors when predicting the erroneous recognition factors by a predicting means.
COPYRIGHT: (C)2006,JPO&NCIPI
摘要翻译：要解决的问题：提供一种用于通过使用户能够直观地理解用户可以改变话语方法的程度来抑制错误识别的发生的语音对话装置，并且还提供语音对话方法。语音对话系统通过语音识别装置（11和14）识别用户的话语，通过话语分析装置（14）分析用户的话语，预测基于错误识别的错误识别因素通过话音分析装置的分析结果，并且通过响应装置（12和14）语音合成包括用户的识别结果的响应，以输出。当通过预测装置预测错误的识别因子时，响应装置通过执行强调错误识别因子的话语转换来进行响应。版权所有（C）2006，JPO＆NCIPI

86. 发明专利

JP2006251059A Voice dialog system and the voice dialog method 有权
标题翻译：语音对话系统和语音对话方法
公开(公告)号：JP2006251059A
公开(公告)日：2006-09-21
申请号：JP2005064223
申请日：2005-03-08
申请人： Hitachi Ltd , Nissan Motor Co Ltd , Xanavi Informatics Corp , 日産自動車株式会社 , 株式会社ザナヴィ・インフォマティクス , 株式会社日立製作所
发明人： ONO TAKESHI , TOGASHI MINORU , TOMOTA TAKAHISA , HATAOKA NOBUO , KUJIRAI TOSHIHIRO
IPC分类号： G10L15/28 , G06F3/16 , G10L15/00 , G10L15/22
摘要： PROBLEM TO BE SOLVED: To provide a voice dialog system for reducing insecurity of a user by intelligibly presenting what role a topic of a current dialog is playing from the point of the whole dialog, and also to provide a voice dialog method. SOLUTION: The voice dialog system comprises: the presentation means (display 5) for promoting utterance of the user by presenting topic information; and the voice recognition means 11 and 14 for recognizing the inputted voice of the user, wherein the dialog with the user is completed after presentation on a plurality of topics by presentation means and voice recognition by voice recognition means. The current topic information is presented on the display 5 as a topic transition process together with connection relationship of the topic information before and after the current topic by a presentation control means 14. COPYRIGHT: (C)2006,JPO&NCIPI
摘要翻译：要解决的问题：提供一种语音对话系统，用于通过从整个对话的角度智能地呈现当前对话的主题的角色来减少用户的不安全性，并且还提供语音对话方法。语音对话系统包括：呈现装置（显示器5），用于通过呈现主题信息来促进用户的话语; 以及用于识别用户的输入语音的语音识别装置11和14，其中在通过呈现装置呈现多个主题并通过语音识别装置的语音识别之后完成与用户的对话。当前主题信息通过呈现控制装置14作为主题转换过程与当前主题之前和之后的主题信息的连接关系呈现在显示器5上。版权所有（C）2006，JPO＆NCIPI

87. 发明专利

JP2003316385A Voice interaction system and voice interaction method 有权
标题翻译：语音交互系统和语音交互方法
公开(公告)号：JP2003316385A
公开(公告)日：2003-11-07
申请号：JP2002122491
申请日：2002-04-24
申请人： Denso Corp , Hitachi Ltd , 株式会社デンソー , 株式会社日立製作所
发明人： HATAOKA NOBUO , WATANABE JUNICHIRO , KUJIRAI TOSHIHIRO , AKAHORI ICHIRO , TATEISHI MASAHIKO , MITAMURA TERUKO , NYBERG ERIC , UENO YOSHIKI
IPC分类号： G01C21/00 , G08G1/137 , G10L15/00 , G10L15/14 , G10L15/22 , G10L15/28
摘要： PROBLEM TO BE SOLVED: To realize inexpensive, efficient, and convenient use of various kinds of on-vehicle information service by realizing free and efficient voice-inputting interaction.
SOLUTION: A task controller 802 generates concretely essential expressions of interaction sequence using, as data, a task document 801 concerning the task of various information to be served. Based on this interaction sequence, concrete interaction dialogs appearing in each task such as a response dialog 806, a time dialog 807, place dialog 808, event site dialog 809 are generated in the form of more detailed interaction dialogs by using an actual time dictionary 8010, a place name dictionary 8011, an event site name dictionary 8012, etc. And, the flow of interaction essential to voice recognition is expressed in a VoiceXML description language or the like to carry out actual interaction services.
COPYRIGHT: (C)2004,JPO
摘要翻译：要解决的问题：通过实现免费高效的语音输入交互，实现廉价，高效，方便地使用各种车载信息服务。解决方案：任务控制器802使用关于要服务的各种信息的任务的任务文档801作为数据来生成具体的交互序列的基本表达。基于该交互序列，通过使用实际时间字典8010，以更详细的交互对话框的形式生成出现在每个任务中的具体交互对话框，诸如响应对话框806，时间对话框807，地方对话框808，事件站点对话框809 ，地名字典8011，事件站点名称字典8012等。此外，语音识别必需的交互流以VoiceXML描述语言等表示，以进行实际的交互服务。版权所有（C）2004，JPO

88. 发明专利

JPH1195789A VOICE RECOGNITION SYSTEM AND SPEAKER ADAPTIVE METHOD IN THE SAME 失效
公开(公告)号：JPH1195789A
公开(公告)日：1999-04-09
申请号：JP25984497
申请日：1997-09-25
申请人： HITACHI LTD
发明人： HATAOKA NOBUO , OBUCHI YASUNARI , ODAKA TOSHIYUKI , AMANO AKIO , EJIRI MASAKAZU , OBA SHINYA
IPC分类号： G10L15/10 , G10L15/00 , G10L15/24 , G10L15/28 , G10L3/00
摘要： PROBLEM TO BE SOLVED: To enable anyone to use a voice recognition system effectively by performing a voice recognition while using the acoustic model of the voice recognition system suited for the feature of a speaker estimated in accordance with a detected physical feature information of the speaker to compensating the degradation of a recognition rate to be caused by depending on feature of the voice of a user. SOLUTION: The feature of the user is extracted from a voice 100 in the personal information extracting part 310 of the voice of the user by using the voice 100 or measured results of a mat type scale 160 and/or a sheet position detecting meter 170 as input information. Moreover, when the measured information of the mat type scale 160 and/or the sheet potion detecting meter are used as the input information, the information are converted into information of a weight or a stature in a physical feature converting part 320 and these are converted into the feature of the voice of the user in a voice feature conversion part 330. Then, a speaker adaptation is executed in a speaker adaptation part 350 for acoustic model so that an acoustic model to be used in the voice recognition becomes the acoustic model suited for the user based on the personal information detected in this manner.

89. 发明专利

JPH10320397A PORTABLE VOICE TRANSLATION TERMINAL 失效
公开(公告)号：JPH10320397A
公开(公告)日：1998-12-04
申请号：JP13191397
申请日：1997-05-22
申请人： HITACHI LTD , HITACHI MICROCOMPUTER SYST
发明人： OHIRA EIJI , HATAOKA NOBUO , TSUKADA TOSHIHISA , KITATSUME YOSHIAKI
IPC分类号： G09F9/35 , G06F17/28 , G10L13/00 , G10L15/00 , G10L3/00
摘要： PROBLEM TO BE SOLVED: To obtain a speech translation terminal which does not lose an advantage that voice has and is easy to use by controlling a voice recognizing means, a speech synthesizing means and a language converting means from an external device when it is confirmed that the terminal is connected to the external device. SOLUTION: Voice that is inputted from a microphone 11 is sampled and inputted by an AD converting part 12. A voice recognizing part in a program in a single operation mode performs characteristic extraction of the inputted voice according to a CPU 1, calculates similarity by using standard patterns of all of sentences and words which you want to make recognized and outputs a sentence (word) of a standard pattern that has the highest similarity as a solution. Also, a translating part retrieves parallel translation of recognition results and an operation type, and when the operation type is a 'sentence', it transfers the recognition results and a parallel translation sentence to a liquid crystal display controlling part 8 and shows them on a liquid crystal display 7. A voice synthesizing part synthesizes synthetic voice from the sent parallel translation sentence, a DA converting part 13 converts it into an analog signal and outputs it from a speaker 14. In this way, if you inputs, e.g. 'OHAYO (Good Morning)' by voice, it answers with 'Good Morning'.

90. 发明专利

JPH1031497A VOICE CONVERSATION CONTROL METHOD AND VOICE CONVERSATION SYSTEM 失效
公开(公告)号：JPH1031497A
公开(公告)日：1998-02-03
申请号：JP18906096
申请日：1996-07-18
申请人： HITACHI LTD
发明人： ODAKA TOSHIYUKI , TORABERUSHI ZUHAERU , AMANO AKIO , HATAOKA NOBUO
IPC分类号： G06F3/16 , G10L15/18 , G10L15/28 , G10L3/00
摘要： PROBLEM TO BE SOLVED: To efficiently conduct voice conversation between a user and a system by eliminating the system output which is for confirmation only and providing the recognition results including a neat guidance sentence. SOLUTION: A conversation control means 5 requests the guidance contents which urge the next action to a task control means 10. The response to the request is a question for a name. Then, the means 5 asks for a latest keyword to a keyword holding means and obtains the 'Material Section' which has been just POPed. Then, the means 5 transmits the next guidance contents and the latest keyword to an response generating means 7 and instructs it to generate a response sentence. Then, the means 7 generates a question sentence, such as 'What is your name in the Material Section?' and transmits the sentence to a voice output means 5. Then, the means 5 sends the recognition vocabulary to a recognition vocabulary supplementing means 3 in order to confirm the name.

你已经成功收藏专利！

检索式保存成功!

IPRDB

热门服务

关于我们

友情链接

联系方式