公开(公告)号：US06978237B2

公开(公告)日：2005-12-20

申请号：US10687707

申请日：2003-10-20

申请人： Mitsuyoshi Tachimori ,  Hiroshi Kanazawa

发明人： Mitsuyoshi Tachimori ,  Hiroshi Kanazawa

IPC分类号： G10L15/22 ,  G01C21/00 ,  G01C21/36 ,  G08G1/0969 ,  G10L15/00 ,  G10L15/26 ,  G10L15/28 ,  G01C21/26

CPC分类号： G01C21/3608 ,  G01C21/3667 ,  G10L15/26 ,  G10L2015/228

摘要： A speech recognition support method in a system to retrieve a map in response to a user's input speech. The user's speech is recognized and a recognition result is obtained. If the recognition result represents a point on the map, a distance between the point and a base point on the map is calculated. The distance is decided to be above a threshold or not. If the distance is above the threshold, an inquiry to confirm whether the recognition result is correct is output to the user.

摘要翻译： 一种用于响应于用户输入语音来检索地图的系统中的语音识别支持方法。 识别用户的语音并获得识别结果。 如果识别结果表示地图上的一个点，则计算地图上点与基点之间的距离。 该距离决定为高于阈值。 如果距离超过阈值，则向用户输出用于确认识别结果是否正确的查询。

公开(公告)号：US20090240500A1

公开(公告)日：2009-09-24

申请号：US12407145

申请日：2009-03-19

申请人： Mitsuyoshi TACHIMORI ,  Shinichi TANAKA

发明人： Mitsuyoshi TACHIMORI ,  Shinichi TANAKA

IPC分类号： G10L15/18

CPC分类号： G10L15/183 ,  G10L2015/228

摘要： A speech recognition apparatus includes a storage unit which store vocabularies, each of vocabularies including plural word body data, each of the word body data obtained by removing a specific word head from a word or sentence, and store at least one word head portion including labeled nodes to express at least one common word head common to at least two of the vocabularies, an instruction receiving unit which receive an instruction of a target vocabulary and an instruction of a operation, a grammar network generating unit which generate, when adding is instructed, a grammar network containing the word head portion, the target vocabulary and connection information indicating that each of the word body data contained in the target vocabulary is connected to a specific one of the labeled nodes contained in the word head portion, and a speech recognition unit which execute speech recognition using the generated grammar network.

摘要翻译： 语音识别装置包括：存储单元，存储词表，每个词汇包括多个单词体数据，通过从单词或句子中去除特定单词头而获得的单词体数据中的每一个，并且存储至少一个单词头部分，包括标记 用于表示至少一个词汇中至少两个共同的公共字头的节点，接收目标词汇表的指令和操作指令的指令接收单元，指示添加时生成的语法网络生成单元， 包含字头部分的语法网络，目标词汇表和连接信息，指示包含在目标词汇表中的每个单词体数据连接到包含在单词头部分中的特定标签节点之一，以及语音识别单元 其使用生成的语法网络执行语音识别。

公开(公告)号：US06718304B1

公开(公告)日：2004-04-06

申请号：US09606150

申请日：2000-06-29

申请人： Mitsuyoshi Tachimori ,  Hiroshi Kanazawa

发明人： Mitsuyoshi Tachimori ,  Hiroshi Kanazawa

IPC分类号： G10L1510

CPC分类号： G01C21/3608 ,  G01C21/3667 ,  G10L15/26 ,  G10L2015/228

摘要： A speech recognition support method in a system to retrieve a map in response to a user's input speech. The user's speech is recognized and a recognition result is obtained. If the recognition result represents a point on the map, a distance between the point and a base point on the map is calculated. The distance is decided to be above a threshold or not. If the distance is above the threshold, an inquiry to confirm whether the recognition result is correct is output to the user.

摘要翻译： 一种用于响应于用户输入语音来检索地图的系统中的语音识别支持方法。 识别用户的语音并获得识别结果。 如果识别结果表示地图上的一个点，则计算地图上点与基点之间的距离。 该距离决定为高于阈值。 如果距离超过阈值，则向用户输出用于确认识别结果是否正确的查询。

公开(公告)号：US08326597B2

公开(公告)日：2012-12-04

申请号：US12560615

申请日：2009-09-16

申请人： Mitsuyoshi Tachimori

发明人： Mitsuyoshi Tachimori

IPC分类号： G06F17/28

CPC分类号： G06F17/289 ,  G06F17/275 ,  G06F17/2854

摘要： A setting unit sets an input language and an output language, a first receiving unit receives input data in a language, a storage unit stores the input data, a detection unit detects a discrepancy between the input language and the language of the input data, a swapping unit swaps the settings of the input language and the output language if the discrepancy is detected, a recognition unit recognizes the input data from the storage unit in the input language set by the setting unit if the discrepancy is not detected, and recognizes the input data read from the storage unit in the input language swapped by the swapping unit if the discrepancy is detected, and a translation unit translates a recognition result recognized in the input language set by the setting unit into the set output language if the discrepancy is not detected, and translates the recognition result recognized in the input language swapped by the swapping unit into the output language swapped by the swapping unit if the discrepancy is detected.

摘要翻译： 设置单元设置输入语言和输出语言，第一接收单元以语言接收输入数据，存储单元存储输入数据，检测单元检测输入语言与输入数据的语言之间的差异， 如果检测到差异，则交换单元交换输入语言和输出语言的设置，如果未检测到差异，则识别单元在由设置单元设置的输入语言中识别来自存储单元的输入数据，并识别输入 如果检测到差异，则由交换单元交换的输入语言从存储单元读取的数据;如果未检测到差异，则翻译单元将由设置单元设置的输入语言识别的识别结果转换为设置输出语言 ，并且将由交换单元交换的输入语言识别的识别结果转换成由交换单元交换的输出语言，如果 检测到差异。

公开(公告)号：US20100198578A1

公开(公告)日：2010-08-05

申请号：US12560615

申请日：2009-09-16

申请人： Mitsuyoshi Tachimori

发明人： Mitsuyoshi Tachimori

IPC分类号： G06F17/28 ,  G06F17/20

CPC分类号： G06F17/289 ,  G06F17/275 ,  G06F17/2854

摘要： A setting unit sets an input language and an output language, a first receiving unit receives input data in a language, a storage unit stores the input data, a detection unit detects a discrepancy between the input language and the language of the input data, a swapping unit swaps the settings of the input language and the output language if the discrepancy is detected, a recognition unit recognizes the input data from the storage unit in the input language set by the setting unit if the discrepancy is not detected, and recognizes the input data read from the storage unit in the input language swapped by the swapping unit if the discrepancy is detected, and a translation unit translates a recognition result recognized in the input language set by the setting unit into the set output language if the discrepancy is not detected, and translates the recognition result recognized in the input language swapped by the swapping unit into the output language swapped by the swapping unit if the discrepancy is detected.

摘要翻译： 设置单元设置输入语言和输出语言，第一接收单元以语言接收输入数据，存储单元存储输入数据，检测单元检测输入语言与输入数据的语言之间的差异， 如果检测到差异，则交换单元交换输入语言和输出语言的设置，如果未检测到差异，则识别单元在由设置单元设置的输入语言中识别来自存储单元的输入数据，并识别输入 如果检测到差异，则由交换单元交换的输入语言从存储单元读取的数据;如果未检测到差异，则翻译单元将由设置单元设置的输入语言识别的识别结果转换为设置输出语言 ，并且将由交换单元交换的输入语言识别的识别结果转换成由交换单元交换的输出语言，如果 检测到差异。

公开(公告)号：US20090299744A1

公开(公告)日：2009-12-03

申请号：US12423215

申请日：2009-04-14

申请人： Mitsuyoshi TACHIMORI

发明人： Mitsuyoshi TACHIMORI

IPC分类号： G10L15/00

CPC分类号： G10L15/063 ,  G10L15/142 ,  G10L25/78

摘要： A voice recognition apparatus determines whether an input sound is a voice segment or a non-voice segment in time series, generates a word model for the voice segment, allocates a predetermined non-voice model for the non-voice segment, connects the word model and the non-voice model in sequence according to the time series of the segments of the input sound corresponding to the respective models and generates a vocalization model, and coordinates the vocalization model with a vocalization ID in one-to-one correspondence, and stores the same.

摘要翻译： 语音识别装置确定输入声音是时间序列中的语音段还是非语音段，生成语音段的单词模型，为非语音段分配预定的非语音模型，连接单词模型 根据与各模型对应的输入声音的段的时间序列顺序地生成非语音模型，并生成发声模型，并以一一对应的方式对发声标识进行协调，并存储 一样。