-
公开(公告)号：US20120166197A1
公开(公告)日：2012-06-28
申请号：US13411614
申请日：2012-03-04
申请人： Guo Kang Fu , Zhao Bing Han , Bin Jia , Ying Liu
发明人： Guo Kang Fu , Zhao Bing Han , Bin Jia , Ying Liu
IPC分类号： G10L15/04
CPC分类号： G10L15/187
摘要： The present invention discloses converting a text form into a speech. In the present invention, partial word lists of a data source are obtained by parsing the data source in parallel or in series. The partial word lists are then compiled to obtain phoneme graphs corresponding, respectively, to the partial word lists, and then the obtained phoneme graphs are combined. Speech recognition is then conducted according to the combination results. According to the present invention, computational complexity may be reduced and recognition efficiency may be improved during speech recognition.
-
2.发明授权公开(公告)号：US08620656B2
公开(公告)日：2013-12-31
申请号：US13411614
申请日：2012-03-04
申请人： Guo Kang Fu , Zhao Bing Han , Bin Jia , Ying Liu
发明人： Guo Kang Fu , Zhao Bing Han , Bin Jia , Ying Liu
CPC分类号： G10L15/187
摘要： The present invention discloses converting a text form into a speech. In the present invention, partial word lists of a data source are obtained by parsing the data source in parallel or in series. The partial word lists are then compiled to obtain phoneme graphs corresponding, respectively, to the partial word lists, and then the obtained phoneme graphs are combined. Speech recognition is then conducted according to the combination results. According to the present invention, computational complexity may be reduced and recognition efficiency may be improved during speech recognition.
摘要翻译： 本发明公开了将文本形式转换为语音。 在本发明中，通过并行或串联解析数据源来获得数据源的部分单词列表。 然后编写部分单词列表以获得分别对应于部分单词列表的音素图，然后组合所获得的音素图。 然后根据组合结果进行语音识别。 根据本发明，可以降低计算复杂度，并且在语音识别期间可以提高识别效率。
-
公开(公告)号：US08650032B2
公开(公告)日：2014-02-11
申请号：US13287400
申请日：2011-11-02
申请人： Guo Kang Fu , Zhao Bing Han , Bin Jia , Ying Liu
发明人： Guo Kang Fu , Zhao Bing Han , Bin Jia , Ying Liu
CPC分类号： G10L15/187
摘要： The present invention discloses converting a text form into a speech. In the present invention, partial word lists of a data source are obtained by parsing the data source in parallel or in series. The partial word lists are then compiled to obtain phoneme graphs corresponding, respectively, to the partial word lists, and then the obtained phoneme graphs are combined. Speech recognition is then conducted according to the combination results. According to the present invention, computational complexity may be reduced and recognition efficiency may be improved during speech recognition.
摘要翻译： 本发明公开了将文本形式转换为语音。 在本发明中，通过并行或串联解析数据源来获得数据源的部分单词列表。 然后编写部分单词列表以获得分别对应于部分单词列表的音素图，然后组合所获得的音素图。 然后根据组合结果进行语音识别。 根据本发明，可以降低计算复杂度，并且在语音识别期间可以提高识别效率。
-
公开(公告)号：US20120136661A1
公开(公告)日：2012-05-31
申请号：US13287400
申请日：2011-11-02
申请人： Guo Kang Fu , Zhao Bing Han , Bin Jia , Ying Liu
发明人： Guo Kang Fu , Zhao Bing Han , Bin Jia , Ying Liu
IPC分类号： G10L15/04
CPC分类号： G10L15/187
摘要： The present invention discloses converting a text form into a speech. In the present invention, partial word lists of a data source are obtained by parsing the data source in parallel or in series. The partial word lists are then compiled to obtain phoneme graphs corresponding, respectively, to the partial word lists, and then the obtained phoneme graphs are combined. Speech recognition is then conducted according to the combination results. According to the present invention, computational complexity may be reduced and recognition efficiency may be improved during speech recognition.
摘要翻译： 本发明公开了将文本形式转换为语音。 在本发明中，通过并行或串联解析数据源来获得数据源的部分单词列表。 然后编写部分单词列表以获得分别对应于部分单词列表的音素图，然后组合所获得的音素图。 然后根据组合结果进行语音识别。 根据本发明，可以降低计算复杂度，并且在语音识别期间可以提高识别效率。
-
公开(公告)号：US20080059156A1
公开(公告)日：2008-03-06
申请号：US11780607
申请日：2007-07-20
申请人： Zhao Bing Han , Guo Kang Fu , Da Lai Yan
发明人： Zhao Bing Han , Guo Kang Fu , Da Lai Yan
IPC分类号： G10L11/04
摘要： A method for processing speech data includes obtaining a pitch and at least one formant frequency for each of a plurality of first speech data; constructing a first feature space with the obtained fundamental frequencies and formant frequencies as features; and classifying the plurality pieces of first speech data using the first feature space, and thus a plurality of speech data classes and the corresponding description are obtained.
摘要翻译： 一种用于处理语音数据的方法包括为多个第一语音数据中的每一个获得音高和至少一个共振峰频率; 构建具有获得的基频和共振峰频率作为特征的第一特征空间; 并且使用第一特征空间对多个第一语音数据进行分类，从而获得多个语音数据类别和相应的描述。
-
6.发明授权公开(公告)号：US07957959B2
公开(公告)日：2011-06-07
申请号：US11780607
申请日：2007-07-20
申请人： Zhao Bing Han , Guo Kang Fu , Da Lai Yan
发明人： Zhao Bing Han , Guo Kang Fu , Da Lai Yan
IPC分类号： G10L11/04
摘要： A method for processing speech data includes obtaining a pitch and at least one formant frequency for each of a plurality of first speech data; constructing a first feature space with the obtained fundamental frequencies and formant frequencies as features; and classifying the plurality pieces of first speech data using the first feature space, and thus a plurality of speech data classes and the corresponding description are obtained.
摘要翻译： 一种用于处理语音数据的方法包括为多个第一语音数据中的每一个获得音高和至少一个共振峰频率; 构建具有获得的基频和共振峰频率作为特征的第一特征空间; 并且使用第一特征空间对多个第一语音数据进行分类，从而获得多个语音数据类别和相应的描述。
-
-
-
-
-
搜索结果
6 条记录 (耗时 0.021 秒)
