公开(公告)号：US06259793B1

公开(公告)日：2001-07-10

申请号：US09030165

申请日：1998-02-25

Applicant: Nobuyuki Washio ,  Yasushi Yamazaki

Inventor： Nobuyuki Washio ,  Yasushi Yamazaki

IPC: H04B100

CPC classification number: H04S1/007

Abstract: An apparatus for continuously reproducing plural sound data has a start end/terminal end determination unit for determining the start end/terminal end of the continued respective sound data, a fade-in/fade-out unit for carrying out fade-in process at the start end of plural respective sound data and/or fade-out process at the terminal end of the same, a data output unit for continuously outputting the plural sound data which have been subjected to fade-in process and/or fade-out process, and a reproduction unit for reproducing the outputted plural sound data. In reproducing continuously the plural sound data, no noise is generated at the joint portion of the adjacent sound data.

Abstract translation: 用于连续再现多个声音数据的装置具有用于确定连续的各个声音数据的起始端/终端的起始端/终端确定单元，用于在该声音数据中执行淡入淡出处理的淡入/淡出单元 在其终端处的多个相应声音数据和/或淡出处理的开始结束，用于连续输出已经进行淡入处理和/或淡出处理的多个声音数据的数据输出单元， 以及再现单元，用于再现所输出的多个声音数据。 在连续重放多个声音数据时，在相邻声音数据的接合部分不产生噪声。

公开(公告)号：US07805304B2

公开(公告)日：2010-09-28

申请号：US11475003

申请日：2006-06-27

Applicant: Nobuyuki Washio

Inventor： Nobuyuki Washio

IPC: G10L15/00 ,  G10L15/20 ,  G10L15/04

CPC classification number: G10L15/22 ,  G10L2015/221

Abstract: A speech recognition apparatus and a method are provided in which even when a speech recognition grammar is employed independently or alternatively, speech recognition response is improved. Voice data is received. Then, an output suspended state for a speech recognition result is maintained until the duration of a silence interval that follows the utterance part reaches a criterion time. Information indicating whether a last word of a word sequence is a final word is stored. On the basis of the language model, a recognition candidate word sequence is extracted. When the last word of the extracted word sequence is determined as being a final word, the speech recognition result is output in a time shorter than the criterion time, while when determined as not being a final word, the speech recognition result is output at the time that the criterion time has elapsed.

Abstract translation: 提供了一种语音识别装置和方法，其中即使独立地或替代地采用语音识别语法，也提高了语音识别响应。 收到语音数据。 然后，保持用于语音识别结果的输出暂停状态，直到发音部分之后的静音间隔的持续时间达到标准时间。 指示字序列的最后一个字是否是最终字的信息被存储。 在语言模型的基础上，提取识别候选词序列。 当提取的字序列的最后一个字被确定为最终字时，语音识别结果在比标准时间短的时间内输出，而当被确定为不是最终字时，语音识别结果在 时间已经过去了。

公开(公告)号：US20100191524A1

公开(公告)日：2010-07-29

申请号：US12754156

申请日：2010-04-05

Applicant: Nobuyuki Washio ,  Shoji Hayakawa

Inventor： Nobuyuki Washio ,  Shoji Hayakawa

IPC: G10L15/20 ,  G10L11/04

CPC classification number: G10L25/78 ,  G10L2025/783

Abstract: A non-speech section detecting device generating a plurality of frames having a given time length on the basis of sound data obtained by sampling sound, and detecting a non-speech section having a frame not containing voice data based on speech uttered by a person, the device including: a calculating part calculating a bias of a spectrum obtained by converting sound data of each frame into components on a frequency axis; a judging part judging whether the bias is greater than or equal to a given threshold or alternatively smaller than or equal to a given threshold; a counting part counting the number of consecutive frames judged as having a bias greater than or equal to the threshold or alternatively smaller than or equal to the threshold; a count judging part judging whether the obtained number of consecutive frames is greater than or equal to a given value.

Abstract translation: 一种非语音部分检测装置，其基于通过采样声音获得的声音数据产生具有给定时间长度的多个帧，并且基于由人发出的语音来检测具有不包含语音数据的帧的非语音部分， 所述装置包括：计算部分，计算通过将每帧的声音数据转换成频率轴上的分量而获得的频谱的偏差; 判断部分判断所述偏差是大于或等于给定阈值还是小于或等于给定阈值; 计数部分，其计算被判断为具有大于或等于所述阈值或者可选地小于或等于所述阈值的偏差的连续帧的数量; 判断所获得的连续帧数是否大于或等于给定值的计数判断部分。

公开(公告)号：US20100169093A1

公开(公告)日：2010-07-01

申请号：US12645476

申请日：2009-12-22

Applicant: Nobuyuki Washio

Inventor： Nobuyuki Washio

IPC: G10L15/06

CPC classification number: G10L15/063 ,  G10L2015/0631

Abstract: An information processing apparatus for speech recognition includes a first speech dataset storing speech data uttered by low recognition rate speakers; a second speech dataset storing speech data uttered by a plurality of speakers; a third speech dataset storing speech data to be mixed with the speech data of the second speech dataset; a similarity calculating part obtaining, for each piece of the speech data in the second speech dataset, a degree of similarity to a given average voice in the first speech dataset; a speech data selecting part recording the speech data, the degree of similarity of which is within a given selection range, as selected speech data in the third speech dataset; and an acoustic model generating part generating a first acoustic model using the speech data recorded in the second speech dataset and the third speech dataset.

Abstract translation: 一种用于语音识别的信息处理设备包括存储由低识别率扬声器发出的语音数据的第一话音数据集; 存储由多个扬声器发出的语音数据的第二话音数据集; 存储要与第二语音数据集的语音数据混合的语音数据的第三语音数据集; 相似度计算部分，对于所述第二语音数据集中的每个所述语音数据，获得与所述第一语音数据集中的给定平均语音的相似度; 语音数据选择部，将其相似度在给定选择范围内的语音数据记录为第三语音数据集中的选定语音数据; 以及使用记录在第二语音数据集和第三语音数据集中的语音数据产生第一声学模型的声学模型生成部分。

公开(公告)号：US07603279B2

公开(公告)日：2009-10-13

申请号：US10347320

申请日：2003-01-21

Applicant: Nobuyuki Washio

Inventor： Nobuyuki Washio

IPC: G10L21/00

CPC classification number: G06F17/2765

Abstract: A grammar update method for storing grammar data for speech interaction used for recognizing speech data and newly recognizing the speech data without using the grammar data, includes determining whether or not a new-recognition result in the newly-recognizing operation can be accepted, and in the case where the new-recognition result cannot be accepted, specifying a portion to be added and updated from the stored grammar data, thereby adding and updating the grammar data.

Abstract translation: 一种语法更新方法，用于存储用于识别语音数据和新识别语音数据的语音交互的语法数据而不使用该语法数据，包括确定新认可操作中的新认可结果是否能被接受，并且 不能接受新的识别结果的情况，从存储的语法数据指定要添加和更新的部分，从而添加和更新语法数据。

公开(公告)号：US20090248412A1

公开(公告)日：2009-10-01

申请号：US12318429

申请日：2008-12-29

Applicant: Nobuyuki Washio

Inventor： Nobuyuki Washio

IPC: G10L17/00

CPC classification number: H04M3/4936 ,  G10L15/26 ,  G10L17/00 ,  H04M2201/405

Abstract: There is provided an association apparatus for associating a plurality of voice data converted from voices produced by speakers, comprising: a word/phrase similarity deriving section which derives an appearance ratio of a common word/phrase that is common among the voice data based on a result of speech recognition processing on the voice data, as a word/phrase similarity; a speaker similarity deriving section which derives a result of comparing characteristics of voices extracted from the voice data, as a speaker similarity; an association degree deriving section which derives a possibility of the plurality of the voice data, which are associated with one another, based on the derived word/phrase similarity and the speaker similarity, as an association degree; and an association section which associates the plurality of the voice data with one another, the derived association degree of which is equal to or more than a preset threshold.

Abstract translation: 提供了一种关联装置，用于将由扬声器产生的语音转换的多个语音数据相关联，包括：词/短语相似性导出部分，其基于语音数据导出语音数据中公共词/短语的出现比 对语音数据进行语音识别处理的结果，作为单词/短语相似性; 扬声器相似性导出部，其导出将从语音数据提取的声音的特性进行比较的结果作为说话者相似度; 基于所导出的词/短语相似度和说话者相似度，将关联于多个语音数据的可能性的关联度导出部分作为关联度; 以及关联部分，其将多个语音数据彼此相关联，导出的关联度等于或大于预设阈值。

公开(公告)号：US09099088B2

公开(公告)日：2015-08-04

申请号：US13064871

申请日：2011-04-21

Applicant: Nobuyuki Washio ,  Shouji Harada ,  Akira Kamano ,  Naoshi Matsuo

Inventor： Nobuyuki Washio ,  Shouji Harada ,  Akira Kamano ,  Naoshi Matsuo

IPC: G10L15/00 ,  G10L17/26 ,  G10L25/48 ,  G10L21/00 ,  G10L13/00 ,  G08B23/00

CPC classification number: G10L17/26 ,  G10L25/48

Abstract: An utterance state detection device includes an user voice stream data input unit that gets user voice stream data of an user, a frequency element extraction unit that extracts high frequency elements by frequency-analyzing the user voice stream data, a fluctuation degree calculation unit that calculates a fluctuation degree of the high frequency elements thus extracted every unit time, a statistic calculation unit that calculates a statistic every certain interval based on a plurality of the fluctuation degrees in a certain period of time, and an utterance state detection unit that detects an utterance state of a specified user based on the statistic obtained from user voice stream data of the specified user.

Abstract translation: 发声状态检测装置包括：用户语音流数据输入单元，其获取用户的用户语音流数据;频率元素提取单元，其通过对用户语音流数据进行频率分析来提取高频元素;波动度计算单元， 每单位时间提取的高频元件的波动程度，统计量计算单元，其基于一定时间段内的多个波动度计算每一定间隔的统计量;以及发声状态检测单元，其检测发音 基于从指定用户的用户语音流数据获得的统计量来指定用户的状态。

公开(公告)号：US08903724B2

公开(公告)日：2014-12-02

申请号：US13363411

申请日：2012-02-01

Applicant: Nobuyuki Washio ,  Shouji Harada

Inventor： Nobuyuki Washio ,  Shouji Harada

IPC: G10L15/08 ,  G10L15/02

CPC classification number: G10L15/02 ,  G10L2015/088

Abstract: A speech recognition device includes, a speech recognition section that conducts a search, by speech recognition, on audio data stored in a first memory section to extract word-spoken portions where plural words transferred are each spoken and, of the word-spoken portions extracted, rejects the word-spoken portion for the word designated as a rejecting object; an acquisition section that obtains a derived word of a designated search target word, the derived word being generated in accordance with a derived word generation rule stored in a second memory section or read out from the second memory section; a transfer section that transfers the derived word and the search target word to the speech recognition section, the derived word being set to the outputting object or the rejecting object by the acquisition section; and an output section that outputs the word-spoken portion extracted and not rejected in the search.

Abstract translation: 一种语音识别装置，包括：语音识别部，其通过语音识别对存储在第一存储器部分中的音频数据进行搜索，以提取每个口令传送多个字的所述语音部分，并且提取所述单词语音部分 拒绝指定为拒绝对象的单词的单词部分; 获取部分，其获得指定搜索目标词的导出词，所述导出词根据存储在第二存储器部分中的从所述第二存储器部分读出的导出词生成规则生成; 将所述导出词和所述搜索目标词传送到所述语音识别部的传送部，所述获取部分被设置到所述输出对象或所述拒绝对象; 以及输出部分，其输出在搜索中提取而不被拒绝的词语部分。

公开(公告)号：US08290773B2

公开(公告)日：2012-10-16

申请号：US12645476

申请日：2009-12-22

Applicant: Nobuyuki Washio

Inventor： Nobuyuki Washio

IPC: G10L15/06

CPC classification number: G10L15/063 ,  G10L2015/0631

Abstract: An information processing apparatus for speech recognition includes a first speech dataset storing speech data uttered by low recognition rate speakers; a second speech dataset storing speech data uttered by a plurality of speakers; a third speech dataset storing speech data to be mixed with the speech data of the second speech dataset; a similarity calculating part obtaining, for each piece of the speech data in the second speech dataset, a degree of similarity to a given average voice in the first speech dataset; a speech data selecting part recording the speech data, the degree of similarity of which is within a given selection range, as selected speech data in the third speech dataset; and an acoustic model generating part generating a first acoustic model using the speech data recorded in the second speech dataset and the third speech dataset.

Abstract translation: 一种用于语音识别的信息处理设备包括存储由低识别率扬声器发出的语音数据的第一话音数据集; 存储由多个扬声器发出的语音数据的第二话音数据集; 存储要与第二语音数据集的语音数据混合的语音数据的第三语音数据集; 相似度计算部分，对于所述第二语音数据集中的每个所述语音数据，获得与所述第一语音数据集中的给定平均语音的相似度; 语音数据选择部，将其相似度在给定选择范围内的语音数据记录为第三语音数据集中的选定语音数据; 以及使用记录在第二语音数据集和第三语音数据集中的语音数据产生第一声学模型的声学模型生成部分。

公开(公告)号：US08195681B2

公开(公告)日：2012-06-05

申请号：US12574270

申请日：2009-10-06

Applicant: Nobuyuki Washio

Inventor： Nobuyuki Washio

IPC: G06F17/30

CPC classification number: G06F17/30241 ,  G01C21/36

Abstract: A searching device includes a history storing unit storing a search target obtained by a search and a search date in a storage unit; a relevancy storing unit storing in the storage unit a previous searching keyword including a plurality of date-related words as well as the search target and an attribute of the search target in association with one another; a change unit changing the previous searching keyword, based on the search date stored in the storage unit and a date output from a clock unit; a reception unit receiving a previous searching keyword and the search target or attribute that are entered by voice; and an extraction unit extracting a search target corresponding to the previous searching keyword and the search target or attribute received by the reception unit, by referring to the previous searching keyword that is obtained after changing, the search target and the attribute.

Abstract translation: 搜索装置包括历史存储单元，其将通过搜索获得的搜索目标和搜索日期存储在存储单元中; 相关性存储单元，其在所述存储单元中存储包括多个日期相关词的先前搜索关键字以及所述搜索目标和所述搜索目标的属性彼此关联; 更改单元，基于存储在存储单元中的搜索日期和从时钟单元输出的日期来改变先前的搜索关键字; 接收单元，接收先前的搜索关键词和通过语音输入的搜索目标或属性; 以及提取单元，通过参考在改变搜索目标和属性之后获得的先前搜索关键字，提取与先前搜索关键词相对应的搜索目标和由接收单元接收的搜索目标或属性。