-
1.发明授权Speech translation apparatus, speech translation method, and non-transitory computer readable medium thereof 有权语音翻译装置，语音翻译方法及其非暂时性计算机可读介质公开(公告)号：US09471568B2
公开(公告)日：2016-10-18
申请号：US14484483
申请日：2014-09-12
发明人： Satoshi Kamatani , Kazuo Sumita , Akinori Kawamura
IPC分类号： G06F17/28 , G10L15/00 , G10L15/065
CPC分类号： G06F17/289 , G10L15/005 , G10L15/065
摘要： According to one embodiment, a speech of a first language is recognized using a speech recognition dictionary to recognize the first language and a second language, and a source sentence of the first language is generated. The source sentence is translated into a second language, and a translation sentence of the second language is generated. An unknown word included in the translation sentence is detected. The unknown word is not stored in the speech recognition dictionary. A first pronunciation candidate of the unknown word is estimated, from a representation of the unknown word. A second pronunciation candidate of the unknown word is estimated from a pronunciation of an original word included in the source sentence corresponding to the unknown word. The unknown word, the first pronunciation candidate and the second pronunciation candidate, are registered into the speech recognition dictionary correspondingly.
摘要翻译： 根据一个实施例，使用语音识别字典识别第一语言的语音以识别第一语言和第二语言，并且生成第一语言的源语句。 源语句被翻译成第二语言，并产生第二语言的翻译句子。 检测到包含在翻译句子中的未知单词。 未知字不存储在语音识别字典中。 从未知词的表示估计未知词的第一个发音候选。 从对应于未知字的源语句中包含的原始词的发音估计未知词的第二发音候选。 未知词，第一发音候选和第二发音候选，相应地登记到语音识别词典中。
-
公开(公告)号：US20130329932A1
公开(公告)日：2013-12-12
申请号：US13680917
申请日：2012-11-19
发明人： Takashi Sudo , Osamu Nishimura , Akihiko Enamito , Takahiro Hiruma , Takafumi Ninomiya , Masaru Sakai , Akinori Kawamura , Kazushige Ouchi
IPC分类号： H04R1/02
CPC分类号： H04R1/02 , H04R1/342 , H04R19/005 , H04R19/016 , H04R2499/15
摘要： According to one embodiment, a sound collector includes a housing and a microphone holding member. The housing includes an opening portion. The opening portion is configured to receive a sound wave having a path. The housing is configured to be tightly closed except the opening portion. The microphone holding member is configured to be provided in the housing and hold a microphone that receives the sound wave propagating through the path at a predetermined position.
摘要翻译： 根据一个实施例，收音机包括壳体和麦克风保持构件。 壳体包括开口部分。 开口部分被配置为接收具有路径的声波。 壳体构造成除了开口部分之外是紧密封闭的。 麦克风保持构件被配置为设置在壳体中并且保持接收在预定位置处通过路径传播的声波的麦克风。
-
3.发明申请SYSTEM AND METHOD FOR TRANSLATING SPEECH, AND NON-TRANSITORY COMPUTER READABLE MEDIUM THEREOF 有权用于翻译语音的系统和方法，以及非终端计算机可读介质公开(公告)号：US20150081274A1
公开(公告)日：2015-03-19
申请号：US14487267
申请日：2014-09-16
发明人： Akinori Kawamura , Kazuo Sumita , Satoshi Kamatani
IPC分类号： G06F17/28
CPC分类号： G06F17/289 , G06F17/28 , G10L15/26
摘要： A first speech input device captures a speech of a first language. A first speech output device outputs another speech of the first language. A second speech input device captures a speech of a second language. A second speech output device outputs another speech of the second language. In a speech recognition/translation server, a first speech recognition device receives a first utterance speech of the first language from the first speech input device, and recognizes the first utterance speech. A first machine translation device consecutively translates the first language of the recognition result into the second language without waiting completion of the first utterance speech. A first speech synthesis device generates a second speech of the translation result. A first output adjustment device outputs the first utterance speech and the second speech to the second speech output device by adjusting a volume of the first utterance speech to be smaller than a volume of the second speech.
摘要翻译： 第一语音输入设备捕获第一语言的语音。 第一语音输出设备输出第一语言的另一语音。 第二语音输入设备捕获第二语言的语音。 第二语音输出设备输出第二语言的另一语音。 在语音识别/翻译服务器中，第一语音识别装置从第一语音输入装置接收第一语言的第一语音语音，并且识别第一话语语音。 第一机器翻译装置将识别结果的第一语言连续地翻译成第二语言，而不等待第一语音的完成。 第一语音合成装置产生翻译结果的第二语音。 第一输出调整装置通过将第一发声语音的音量调整为小于第二语音的音量，将第一发声和第二语音输出到第二语音输出装置。
-
4.发明授权Speech translation apparatus, speech translation method, and non-transitory computer readable medium thereof 有权语音翻译装置，语音翻译方法及其非暂时性计算机可读介质公开(公告)号：US09484017B2
公开(公告)日：2016-11-01
申请号：US14484494
申请日：2014-09-12
发明人： Kazuo Sumita , Akinori Kawamura , Satoshi Kamatani
摘要： A first speech processing device includes a first speech input unit and a first speech output unit. A second speech processing device includes a second speech input unit and a second speech output unit. In a server therebetween, a speech of a first language sent from the first speech input unit is recognized. The speech recognition result is translated into a second language. The translation result is back translated into the first language. A first speech synthesis signal of the back translation result is sent to the first speech output unit. A second speech synthesis signal of the translation result is sent to the second speech output unit. Duration of the second speech synthesis signal or the first speech synthesis signal is measured. The first speech synthesis signal and the second speech synthesis signal are outputted by synchronizing a start time and an end time thereof, based on the duration.
摘要翻译： 第一语音处理装置包括第一语音输入单元和第一语音输出单元。 第二语音处理装置包括第二语音输入单元和第二语音输出单元。 在其间的服务器中，识别从第一语音输入单元发送的第一语言的语音。 语音识别结果被翻译成第二语言。 翻译结果被翻译成第一语言。 将后翻译结果的第一语音合成信号发送到第一语音输出单元。 翻译结果的第二语音合成信号被发送到第二语音输出单元。 测量第二语音合成信号或第一语音合成信号的持续时间。 基于持续时间，第一语音合成信号和第二语音合成信号通过使开始时间和结束时间同步来输出。
-
5.发明申请CONVERSATION SUPPORTING DEVICE, CONVERSATION SUPPORTING METHOD AND CONVERSATION SUPPORTING PROGRAM 审中-公开对话支持设备，对话支持方法和对话支持程序公开(公告)号：US20130253932A1
公开(公告)日：2013-09-26
申请号：US13776344
申请日：2013-02-25
发明人： Masahide ARIU , Kazuo Sumita , Akinori Kawamura
IPC分类号： G10L15/22
CPC分类号： G10L15/22 , G10L15/26 , G10L2015/227
摘要： A conversation supporting device of an embodiment of the present disclosure has a information storage unit, a recognition resource constructing unit, and a voice recognition unit. Here, the information storage unit stores the information disclosed by a speaker. The recognition resource constructing unit uses the disclosed information to construct the recognition resource including a voice model and a language model for recognition of voice data. The voice recognition unit uses the recognition resource to recognize the voice data.
摘要翻译： 本公开的实施例的会话支持装置具有信息存储单元，识别资源构成单元和语音识别单元。 这里，信息存储单元存储由扬声器公开的信息。 识别资源构成单元使用所公开的信息来构建识别资源，包括用于识别语音数据的语音模型和语言模型。 语音识别单元使用识别资源识别语音数据。
-
6.发明授权System and method for translating speech, and non-transitory computer readable medium thereof 有权用于翻译语音的系统和方法及其非暂时性计算机可读介质公开(公告)号：US09280539B2
公开(公告)日：2016-03-08
申请号：US14487267
申请日：2014-09-16
发明人： Akinori Kawamura , Kazuo Sumita , Satoshi Kamatani
CPC分类号： G06F17/289 , G06F17/28 , G10L15/26
摘要： A first speech input device captures a speech of a first language. A first speech output device outputs another speech of the first language. A second speech input device captures a speech of a second language. A second speech output device outputs another speech of the second language. In a speech recognition/translation server, a first speech recognition device receives a first utterance speech of the first language from the first speech input device, and recognizes the first utterance speech. A first machine translation device consecutively translates the first language of the recognition result into the second language without waiting completion of the first utterance speech. A first speech synthesis device generates a second speech of the translation result. A first output adjustment device outputs the first utterance speech and the second speech to the second speech output device by adjusting a volume of the first utterance speech to be smaller than a volume of the second speech.
摘要翻译： 第一语音输入设备捕获第一语言的语音。 第一语音输出设备输出第一语言的另一语音。 第二语音输入设备捕获第二语言的语音。 第二语音输出设备输出第二语言的另一语音。 在语音识别/翻译服务器中，第一语音识别装置从第一语音输入装置接收第一语言的第一语音语音，并且识别第一话语语音。 第一机器翻译装置将识别结果的第一语言连续地翻译成第二语言，而不等待第一语音的完成。 第一语音合成装置产生翻译结果的第二语音。 第一输出调整装置通过将第一发声语音的音量调整为小于第二语音的音量，将第一发声和第二语音输出到第二语音输出装置。
-
7.发明申请SPEECH TRANSLATION APPARATUS, SPEECH TRANSLATION METHOD, AND NON-TRANSITORY COMPUTER READABLE MEDIUM THEREOF 有权语音翻译设备，语音翻译方法和非终端计算机可读介质公开(公告)号：US20150081271A1
公开(公告)日：2015-03-19
申请号：US14484494
申请日：2014-09-12
发明人： Kazuo Sumita , Akinori Kawamura , Satoshi Kamatani
摘要： A first speech processing device includes a first speech input unit and a first speech output unit. A second speech processing device includes a second speech input unit and a second speech output unit. In a server therebetween, a speech of a first language sent from the first speech input unit is recognized. The speech recognition result is translated into a second language. The translation result is back translated into the first language. A first speech synthesis signal of the back translation result is sent to the first speech output unit. A second speech synthesis signal of the translation result is sent to the second speech output unit. Duration of the second speech synthesis signal or the first speech synthesis signal is measured. The first speech synthesis signal and the second speech synthesis signal are outputted by synchronizing a start time and an end time thereof, based on the duration.
摘要翻译： 第一语音处理装置包括第一语音输入单元和第一语音输出单元。 第二语音处理装置包括第二语音输入单元和第二语音输出单元。 在其间的服务器中，识别从第一语音输入单元发送的第一语言的语音。 语音识别结果被翻译成第二语言。 翻译结果被翻译成第一语言。 将后翻译结果的第一语音合成信号发送到第一语音输出单元。 翻译结果的第二语音合成信号被发送到第二语音输出单元。 测量第二语音合成信号或第一语音合成信号的持续时间。 基于持续时间，第一语音合成信号和第二语音合成信号通过使开始时间和结束时间同步来输出。
-
8.发明申请SPEECH TRANSLATION APPARATUS, SPEECH TRANSLATION METHOD, AND NON-TRANSITORY COMPUTER READABLE MEDIUM THEREOF 有权语音翻译设备，语音翻译方法和非终端计算机可读介质公开(公告)号：US20150081270A1
公开(公告)日：2015-03-19
申请号：US14484483
申请日：2014-09-12
发明人： Satoshi Kamatani , Kazuo Sumita , Akinori Kawamura
IPC分类号： G06F17/28
CPC分类号： G06F17/289 , G10L15/005 , G10L15/065
摘要： According to one embodiment, a speech of a first language is recognized using a speech recognition dictionary to recognize the first language and a second language, and a source sentence of the first language is generated. The source sentence is translated into a second language, and a translation sentence of the second language is generated. An unknown word included in the translation sentence is detected. The unknown word is not stored in the speech recognition dictionary. A first pronunciation candidate of the unknown word is estimated, from a representation of the unknown word. A second pronunciation candidate of the unknown word is estimated from a pronunciation of an original word included in the source sentence corresponding to the unknown word. The unknown word, the first pronunciation candidate and the second pronunciation candidate, are registered into the speech recognition dictionary correspondingly.
摘要翻译： 根据一个实施例，使用语音识别字典识别第一语言的语音以识别第一语言和第二语言，并且生成第一语言的源语句。 源语句被翻译成第二语言，并产生第二语言的翻译句子。 检测到包含在翻译句子中的未知单词。 未知字不存储在语音识别字典中。 从未知词的表示估计未知词的第一个发音候选。 从对应于未知字的源语句中包含的原始词的发音估计未知词的第二发音候选。 未知词，第一发音候选和第二发音候选，相应地登记到语音识别词典中。
-
-
-
-
-
-
-
搜索结果
8 条记录 (耗时 0.014 秒)
