-
-
Patent Agency Ranking
公开(公告)号：KR1020140098525A
公开(公告)日：2014-08-08
申请号：KR1020130011292
申请日：2013-01-31
Applicant: 삼성전자주식회사
CPC classification number: G10L15/08 , G06F17/2705 , G10L15/22 , G10L2015/223
Abstract: A speech recognition apparatus and a method to provide response information are disclosed. According to the present invention, the speech recognition apparatus comprises: an extraction unit to extract a first speech component indicating an execution instruction and a second speed component indicating an object from a speech signal of a user; a domain determination unit to detect an extended domain associated with the extracted first and second speech components based on a preset hierarchical domain model, and determining at least one candidate domain associated with the detected extended domain as a final domain; a communications unit to perform communication with an external device; and a control unit to control the communications unit so as to transmit information on the first and second speech components and information on the determined final domain. Therefore, it is possible to determine a domain suitable for a user′s intent, and provide response information with respect to the user′s speech.
Abstract translation: 公开了一种提供响应信息的语音识别装置和方法。 根据本发明，语音识别装置包括：提取单元，用于从用户的语音信号中提取指示执行指令的第一语音分量和指示对象的第二速度分量; 域确定单元，用于基于预设的分级域模型来检测与所提取的第一和第二语音组件相关联的扩展域，以及将与所检测的扩展域相关联的至少一个候选域确定为最终域; 通信单元，用于执行与外部设备的通信; 以及控制单元，用于控制通信单元，以便发送关于第一和第二语音分量的信息以及关于确定的最终域的信息。 因此，可以确定适合于用户意图的域，并且提供关于用户的语音的响应信息。
-
公开(公告)号：KR102211595B1
公开(公告)日：2021-02-04
申请号：KR1020130151129
申请日：2013-12-06
Applicant: 삼성전자주식회사
Abstract: 음성인식장치및 그제어방법이개시된다. 본발명에따르면, 음성인식장치는사용자의발화음성으로부터실행명령을나타내는제1 발화요소및 대상을나타내는제2 발화요소중 적어도하나를추출하는추출부, 제1 및제2 발화요소에기초하여발화음성에대한응답정보를제공하기위한현재도메인을결정하는도메인결정부및 현재도메인과사용자의이전발화음성으로부터기결정된이전도메인상에서의대화상태에기초하여현재도메인및 이전도메인중 적어도하나의도메인상에서발화음성에대한응답정보를제공하기위한후보대화프레임을결정하는제어부를포함한다. 이에따라, 음성인식장치는사용자의발화음성에대해서다양한경우의수를고려하여사용자의도에적합한응답정보를제공할수 있다.
-
公开(公告)号：KR1020140074229A
公开(公告)日：2014-06-17
申请号：KR1020130151129
申请日：2013-12-06
Applicant: 삼성전자주식회사
CPC classification number: G10L15/22 , G10L15/1822 , G10L2015/228
Abstract: Disclosed are a voice recognition device and a control method thereof. According to the present invention, the voice recognition device includes: an extraction unit which extracts one among a first speech element which indicates an execution order from the speech of a user and a second speech element which indicates a target; a domain determination unit which determines the current domain to provide response data for the speech based on the first and the second speech element; and a control unit which determines a dialog frame candidate to provide response data for the speech on at least one among the current domain and the previous domain based on the dialog status on the current domain and a predetermined previous domain from the previous speech of the user. By doing so, the voice recognition device is able to provide response data appropriate for user intention in consideration of a large number of cases for speeches from a user.
Abstract translation: 公开了一种语音识别装置及其控制方法。 根据本发明，语音识别装置包括：提取单元，从指示用户的语音的指示执行顺序的第一语音单元和表示目标的第二语音单元中提取单元; 域确定单元，其基于第一和第二语音元素确定当前域以提供用于语音的响应数据; 以及控制单元，其基于当前域的对话状态和来自用户的先前语音的预定的先前域，确定在当前域和先前域中的至少一个上为语音提供语音的响应数据的对话框候选 。 通过这样做，考虑到来自用户的演讲的大量情况，语音识别装置能够提供适合于用户意图的响应数据。
-
公开(公告)号：KR1020140054643A
公开(公告)日：2014-05-09
申请号：KR1020120120374
申请日：2012-10-29
Applicant: 삼성전자주식회사
Abstract: A voice recognition apparatus according to the present invention comprises a voice receiving part which receives the voice signal of a user; a first voice recognition engine which receives the voice signal and performs a voice recognition process; a communication part which receives the voice signal and transmits the voice signal to an external second voice recognition engine; and a control part which controls the transmission of the voice signal received by the voice receiving part so that the voice signal is transmitted to one among the first voice recognition engine and the communication part, based on the selection of the user.
Abstract translation: 根据本发明的语音识别装置包括接收用户的语音信号的语音接收部分; 第一语音识别引擎，其接收语音信号并执行语音识别处理; 通信部件，其接收所述语音信号并将所述语音信号发送到外部第二语音识别引擎; 以及控制部，其基于所述用户的选择，控制由所述语音接收部接收到的语音信号的发送，使得所述语音信号被发送到所述第一语音识别引擎和所述通信部中的一个。
-
公开(公告)号：KR1020130045471A
公开(公告)日：2013-05-06
申请号：KR1020110109694
申请日：2011-10-26
Applicant: 삼성전자주식회사
CPC classification number: G10L15/26
Abstract: PURPOSE: An electronic device and a control method are provided to enable a user to conveniently use various communication functions by utilizing home appliances. CONSTITUTION: A voice input unit(11) receives user voice. A signal processing unit(12) processes a signal for the user voice. A communication unit(14) communicates with a first external device. A control unit(15) determines a text corresponding to the user voice and transmits the user voice and the text to the first external device. [Reference numerals] (1) Electronic device; (11) Voice input unit; (12) Signal processing unit; (13) Display unit; (14) Communication unit; (15) Control unit; (16) Storage unit; (17) User input unit; (18) Voice output unit; (AA) User voice; (BB) Voice/text; (CC) Voice recognition information; (DD) User command
Abstract translation: 目的：提供电子设备和控制方法，使用户能够通过利用家用电器方便地使用各种通信功能。 声明：语音输入单元（11）接收用户声音。 信号处理单元（12）处理用户语音的信号。 通信单元（14）与第一外部设备通信。 控制单元（15）确定与用户语音相对应的文本，并将用户语音和文本发送到第一外部设备。 （附图标记）（1）电子设备; （11）语音输入单元; （12）信号处理单元; （13）显示单元; （14）通讯单元; （15）控制单元; （16）存储单元; （17）用户输入单元; （18）语音输出单元; （AA）用户声音; （BB）语音/文字; （CC）语音识别信息; （DD）用户指令
-
-
-
-
-
Search Results
6
records
(took 0.02 seconds)
