公开(公告)号：US07765102B2

公开(公告)日：2010-07-27

申请号：US12171309

申请日：2008-07-11

申请人： David Mowatt ,  Robert Chambers ,  Ciprian Chelba ,  Qiang Wu

发明人： David Mowatt ,  Robert Chambers ,  Ciprian Chelba ,  Qiang Wu

IPC分类号： G10L15/00

CPC分类号： G10L15/183

摘要： A system and method for creating a mnemonics Language Model for use with a speech recognition software application, wherein the method includes generating an n-gram Language Model containing a predefined large body of characters, wherein the n-gram Language Model includes at least one character from the predefined large body of characters, constructing a new Language Model (LM) token for each of the at least one character, extracting pronunciations for each of the at least one character responsive to a predefined pronunciation dictionary to obtain a character pronunciation representation, creating at least one alternative pronunciation for each of the at least one character responsive to the character pronunciation representation to create an alternative pronunciation dictionary and compiling the n-gram Language Model for use with the speech recognition software application, wherein compiling the Language Model is responsive to the new Language Model token and the alternative pronunciation dictionary.

摘要翻译： 一种用于创建与语音识别软件应用一起使用的助记符语言模型的系统和方法，其中所述方法包括生成包含预定义的大量字符的n-gram语言模型，其中所述n-gram语言模型包括至少一个字符 从所述预定义的大量字符中，为所述至少一个字符中的每一个构造新的语言模型（LM）令牌，响应于预定义的发音字典提取所述至少一个字符中的每个字符的发音，以获得字符发音表示，创建 响应于字符发音表示的至少一个字符中的每一个的至少一个替代发音，以创建替代发音字典并且编译用于语音识别软件应用的n-gram语言模型，其中编译语言模型响应于 新的语言模型标记和替代发音 词典。

公开(公告)号：US20080319749A1

公开(公告)日：2008-12-25

申请号：US12171309

申请日：2008-07-11

申请人： David Mowatt ,  Robert Chambers ,  Ciprian Chelba ,  Qiang Wu

发明人： David Mowatt ,  Robert Chambers ,  Ciprian Chelba ,  Qiang Wu

IPC分类号： G10L15/04

CPC分类号： G10L15/183

摘要： A system and method for creating a mnemonics Language Model for use with a speech recognition software application, wherein the method includes generating an n-gram Language Model containing a predefined large body of characters, wherein the n-gram Language Model includes at least one character from the predefined large body of characters, constructing a new Language Model (LM) token for each of the at least one character, extracting pronunciations for each of the at least one character responsive to a predefined pronunciation dictionary to obtain a character pronunciation representation, creating at least one alternative pronunciation for each of the at least one character responsive to the character pronunciation representation to create an alternative pronunciation dictionary and compiling the n-gram Language Model for use with the speech recognition software application, wherein compiling the Language Model is responsive to the new Language Model token and the alternative pronunciation dictionary.

摘要翻译： 一种用于创建与语音识别软件应用一起使用的助记符语言模型的系统和方法，其中所述方法包括生成包含预定义的大量字符的n-gram语言模型，其中所述n-gram语言模型包括至少一个字符 从所述预定义的大量字符中，为所述至少一个字符中的每一个构造新的语言模型（LM）令牌，响应于预定义的发音字典提取所述至少一个字符中的每个字符的发音，以获得字符发音表示，创建 响应于字符发音表示的至少一个字符中的每一个的至少一个替代发音，以创建替代发音字典并且编译用于语音识别软件应用的n-gram语言模型，其中编译语言模型响应于 新的语言模型标记和替代发音 词典。

公开(公告)号：US20060111907A1

公开(公告)日：2006-05-25

申请号：US10996732

申请日：2004-11-24

申请人： David Mowatt ,  Robert Chambers ,  Ciprian Chelba ,  Qiang Wu

发明人： David Mowatt ,  Robert Chambers ,  Ciprian Chelba ,  Qiang Wu

IPC分类号： G10L15/18

CPC分类号： G10L15/183

摘要： A system and method for creating a mnemonics Language Model for use with a speech recognition software application, wherein the method includes generating an n-gram Language Model containing a predefined large body of characters, wherein the n-gram Language Model includes at least one character from the predefined large body of characters, constructing a new language Model (LM) token for each of the at least one character, extracting pronunciations for each of the at least one character responsive to a predefined pronunciation dictionary to obtain a character pronunciation representation, creating at least one alternative pronunciation for each of the at least one character responsive to the character pronunciation representation to create an alternative pronunciation dictionary and compiling the n-gram Language Model for use with the speech recognition software application, wherein compiling the Language Model is responsive to the new Language Model token and the alternative pronunciation dictionary.

摘要翻译： 一种用于创建与语音识别软件应用一起使用的助记符语言模型的系统和方法，其中所述方法包括生成包含预定义的大量字符的n-gram语言模型，其中所述n-gram语言模型包括至少一个字符 从所述预定义的大量字符中，为所述至少一个字符中的每一个构造新语言模型（LM）令牌，响应于预定义的发音字典提取所述至少一个字符中的每个字符的发音以获得字符发音表示，创建 响应于字符发音表示的至少一个字符中的每一个的至少一个替代发音，以创建替代发音字典并且编译用于语音识别软件应用的n-gram语言模型，其中编译语言模型响应于 新的语言模型标记和替代发音 词典。

公开(公告)号：US07418387B2

公开(公告)日：2008-08-26

申请号：US10996732

申请日：2004-11-24

申请人： David Mowatt ,  Robert Chambers ,  Ciprian Chelba ,  Qiang Wu

发明人： David Mowatt ,  Robert Chambers ,  Ciprian Chelba ,  Qiang Wu

IPC分类号： G10L15/18

CPC分类号： G10L15/183

摘要： A system and method for creating a mnemonics Language Model for use with a speech recognition software application, wherein the method includes generating an n-gram Language Model containing a predefined large body of characters, wherein the n-gram Language Model includes at least one character from the predefined large body of characters, constructing a new language Model (LM) token for each of the at least one character, extracting pronunciations for each of the at least one character responsive to a predefined pronunciation dictionary to obtain a character pronunciation representation, creating at least one alternative pronunciation for each of the at least one character responsive to the character pronunciation representation to create an alternative pronunciation dictionary and compiling the n-gram Language Model for use with the speech recognition software application, wherein compiling the Language Model is responsive to the new Language Model token and the alternative pronunciation dictionary.

摘要翻译： 一种用于创建与语音识别软件应用一起使用的助记符语言模型的系统和方法，其中所述方法包括生成包含预定义的大量字符的n-gram语言模型，其中所述n-gram语言模型包括至少一个字符 从所述预定义的大量字符中，为所述至少一个字符中的每一个构造新语言模型（LM）令牌，响应于预定义的发音字典提取所述至少一个字符中的每个字符的发音以获得字符发音表示，创建 响应于字符发音表示的至少一个字符中的每一个的至少一个替代发音，以创建替代发音字典并且编译用于语音识别软件应用的n-gram语言模型，其中编译语言模型响应于 新的语言模型标记和替代发音 词典。

公开(公告)号：US20080059186A1

公开(公告)日：2008-03-06

申请号：US11513772

申请日：2006-08-31

申请人： David Mowatt ,  Ricky Loynd ,  Robert Edward Dewar ,  Rachel Imogen Morton ,  Qiang Wu ,  Robert Ian Brown ,  Michael D. Plumpe ,  Philipp Heinz Schmid

发明人： David Mowatt ,  Ricky Loynd ,  Robert Edward Dewar ,  Rachel Imogen Morton ,  Qiang Wu ,  Robert Ian Brown ,  Michael D. Plumpe ,  Philipp Heinz Schmid

IPC分类号： G10L15/18

CPC分类号： G10L15/193 ,  G10L2015/223

摘要： Intelligent speech recognition is used to provide users with the ability to utter more user friendly commands. Satisfaction is increased when a user can vocalize a subset of a formal command name and still have the intended command identified and processed. Moreover, greater accuracy in identifying a command application from a user's utterance can be achieved by ignoring command choices associated with unlikely user utterances. An intelligent speech recognition system can identify differing acceptable verbal command phrase forms, e.g., but not limited to, complete commands, command subsequences and command subsets, for different commands supported by the system. Subset blocking words are identified for assistance in reducing the ambiguity in matching user verbal command phrases with valid commands supported by the intelligent speech recognition system.

摘要翻译： 智能语音识别用于为用户提供更多用户友好命令的能力。 当用户能够发出正式命令名称的子集并且仍然具有识别和处理的预期命令时，满意度就会增加。 此外，通过忽略与不太可能的用户话语相关联的命令选择，可以实现从用户的话语识别命令应用程序的更高精度。 智能语音识别系统可以识别用于系统支持的不同命令的不同的可接受的口头命令短语形式，例如但不限于完整的命令，命令子序列和命令子集。 识别子集阻塞字以帮助减少用户语言命令短语与由智能语音识别系统支持的有效命令的模糊性。

公开(公告)号：US07949536B2

公开(公告)日：2011-05-24

申请号：US11513772

申请日：2006-08-31

申请人： David Mowatt ,  Ricky Loynd ,  Robert Edward Dewar ,  Rachel Imogen Morton ,  Qiang Wu ,  Robert Ian Brown ,  Michael D. Plumpe ,  Philipp Heinz Schmid

发明人： David Mowatt ,  Ricky Loynd ,  Robert Edward Dewar ,  Rachel Imogen Morton ,  Qiang Wu ,  Robert Ian Brown ,  Michael D. Plumpe ,  Philipp Heinz Schmid

IPC分类号： G10L21/00

CPC分类号： G10L15/193 ,  G10L2015/223

摘要： Intelligent speech recognition is used to provide users with the ability to utter more user friendly commands. Satisfaction is increased when a user can vocalize a subset of a formal command name and still have the intended command identified and processed. Moreover, greater accuracy in identifying a command application from a user's utterance can be achieved by ignoring command choices associated with unlikely user utterances. An intelligent speech recognition system can identify differing acceptable verbal command phrase forms, e.g., but not limited to, complete commands, command subsequences and command subsets, for different commands supported by the system. Subset blocking words are identified for assistance in reducing the ambiguity in matching user verbal command phrases with valid commands supported by the intelligent speech recognition system.

摘要翻译： 智能语音识别用于为用户提供更多用户友好命令的能力。 当用户能够发出正式命令名称的子集并且仍然具有识别和处理的预期命令时，满意度就会增加。 此外，通过忽略与不太可能的用户话语相关联的命令选择，可以实现从用户的话语识别命令应用程序的更高精度。 智能语音识别系统可以识别用于系统支持的不同命令的不同的可接受的口头命令短语形式，例如但不限于完整的命令，命令子序列和命令子集。 识别子集阻塞字以帮助减少用户语言命令短语与由智能语音识别系统支持的有效命令的模糊性。

公开(公告)号：US08082145B2

公开(公告)日：2011-12-20

申请号：US12825006

申请日：2010-06-28

申请人： David Mowatt ,  Robert Chambers ,  Felix GTI Andrew

发明人： David Mowatt ,  Robert Chambers ,  Felix GTI Andrew

IPC分类号： G06F17/27

CPC分类号： G06F3/167 ,  G10L2015/221

摘要： Embodiments for manipulating characters displayed on a display screen are provided, wherein one example method includes identifying a selected word, wherein the selected word includes at least one character to be modified. The method further includes correlating each of the at least one character with a unique numerical value and receiving a selection command and a modification command, wherein the selection command is the unique numerical value corresponding to a selected character. Furthermore, the method includes modifying the selected character responsive to the modification command to generate a modified word.

摘要翻译： 提供了用于操纵显示在显示屏幕上的字符的实施例，其中一个示例性方法包括识别所选择的单词，其中所选择的单词包括至少一个要修改的字符。 该方法还包括将至少一个字符中的每一个与唯一的数值进行关联，并接收选择命令和修改命令，其中所述选择命令是对应于所选择的字符的唯一数值。 此外，该方法包括响应于修改命令修改所选择的字符以生成修改的字。

公开(公告)号：US20070218955A1

公开(公告)日：2007-09-20

申请号：US11378550

申请日：2006-03-17

申请人： Daniel Cook ,  David Mowatt ,  Oliver Scholz ,  Oscar Murillo ,  Robert Chambers ,  Ryan Bickel

发明人： Daniel Cook ,  David Mowatt ,  Oliver Scholz ,  Oscar Murillo ,  Robert Chambers ,  Ryan Bickel

IPC分类号： H04B1/38

CPC分类号： G10L15/28 ,  H04M1/6066 ,  H04M2250/74

摘要： A portable wireless-enabled system includes an input transducer (for example, a microphone), an output transducer (for example, a speaker) and a wireless transceiver system. Also included, is a memory having a programmable user speech profile. A processor system controls operation of the input transducer, the output transducer, the wireless transceiver system and the memory.

摘要翻译： 便携式无线系统包括输入换能器（例如，麦克风），输出换能器（例如扬声器）和无线收发器系统。 还包括，是具有可编程用户语音简档的存储器。 处理器系统控制输入传感器，输出变换器，无线收发器系统和存储器的操作。

公开(公告)号：US07778821B2

公开(公告)日：2010-08-17

申请号：US10997255

申请日：2004-11-24

申请人： David Mowatt ,  Robert Chambers ,  Felix GTI Andrew

发明人： David Mowatt ,  Robert Chambers ,  Felix GTI Andrew

IPC分类号： G06F17/21

CPC分类号： G06F3/167 ,  G10L2015/221

摘要： A method and system for manipulating characters displayed on a display screen is provided wherein the method includes identifying a selected word, wherein the selected word includes at least one character to be modified. The method further includes correlating each of the at least one character with a unique numerical value and receiving a selection command and a modification command, wherein the selection command is the unique numerical value corresponding to a selected character. Furthermore, the method includes modifying the selected character responsive to the modification command to generate a modified word.

摘要翻译： 提供了一种用于操纵显示在显示屏幕上的字符的方法和系统，其中所述方法包括识别所选择的单词，其中所选择的单词包括至少一个要修改的字符。 该方法还包括将至少一个字符中的每一个与唯一的数值进行关联，并接收选择命令和修改命令，其中所述选择命令是对应于所选择的字符的唯一数值。 此外，该方法包括响应于修改命令修改所选择的字符以生成修改的字。

公开(公告)号：US20070033037A1

公开(公告)日：2007-02-08

申请号：US11255329

申请日：2005-10-21

申请人： David Mowatt ,  Robert Dewar ,  Robert Chambers ,  Felix Torquil Ifor Andrew

发明人： David Mowatt ,  Robert Dewar ,  Robert Chambers ,  Felix Torquil Ifor Andrew

IPC分类号： G10L15/04

CPC分类号： G10L15/22

摘要： Upon selection of a displayed word, a list of alternatives for the selected word is displayed. Each alternative in the list has an associated symbol. A speech signal is then decoded to identify a list of possible words and the list of possible words is displayed with each possible word having an associated symbol.

摘要翻译： 在选择所显示的单词时，显示所选择的单词的替换列表。 列表中的每个替代项都有一个关联的符号。 然后解码语音信号以识别可能的词的列表，并且显示可能的词的列表，每个可能的单词具有相关联的符号。