公开(公告)号：US5208863A

公开(公告)日：1993-05-04

申请号：US608376

申请日：1990-11-02

申请人： Atsushi Sakurai ,  Junichi Tamura ,  Tetsuo Kosaka

发明人： Atsushi Sakurai ,  Junichi Tamura ,  Tetsuo Kosaka

IPC分类号： G10L13/06 ,  G10L15/02 ,  G10L19/00

CPC分类号： G10L15/02

摘要： A method for encoding syllables of a language, particularly the Japanese language, and for facilitating the extraction of sound codes from the input syllables, for voice recognition or voice synthesis includes the step of providing a syllable classifying table, in which each syllable is represented by an upper byte code indicating the consonant part of the syllable and a lower byte code indicating the non-consonant part of the syllable. The consonants constitute a first category of data classified by phonetic features, while the non-consonants constitute a second category of data classified by phonetic features, so that the extraction of consonant or non-consonant sounds can be made by a search in only the first or the second categories. The encoding of diphthongs are made in such a manner that those containing the same vowel have the same remainder corresponding to the code of this vowel, when the codes are divided by the number of vowels contained in the second category, so that the extraction of a vowel from diphthongs can be achieved by a simple mathematical division.

摘要翻译： 用于编码语言，特别是日语的音节的方法，以及用于便于从输入音节提取声音代码，用于语音识别或语音合成的方法包括提供音节分类表的步骤，其中每个音节由 指示音节的辅音部分的高字节代码和表示音节的非辅音部分的低字节代码。 辅音构成了以语音特征分类的第一类数据，而非辅音构成了以语音特征分类的第二类数据，因此可以仅通过搜索第一类搜索辅音或非辅音 或第二类。 双符号的编码是这样进行的，即当包含同一元音的那些元素具有与该元音的代码相同的余数时，当代码除以第二类别中包含的元音数量，从而提取 来自diphthongs的元音可以通过简单的数学部分来实现。

公开(公告)号：US06236964B1

公开(公告)日：2001-05-22

申请号：US08194807

申请日：1994-02-14

申请人： Junichi Tamura ,  Tetsuo Kosaka ,  Atsushi Sakurai

发明人： Junichi Tamura ,  Tetsuo Kosaka ,  Atsushi Sakurai

IPC分类号： G10L506

CPC分类号： G10L15/10 ,  G10L2015/025

摘要： A speech recognition method and apparatus in which a speech section is sliced by the unit of a word by spotting and candidate words are selected. Next, in a second stage, matching is conducted by the unit of a phoneme. Consequently, selection of the candidate words and slicing of the speech section can be performed concurrently. Furthermore, narrowing of the candidate words is facilitated. Furthermore, since reference phoneme patterns under a plurality of environments are prepared, recognition of an input speech under a larger number of conditions is possible using a smaller amount of data when compared with the case in which reference word patterns under a plurality of environments are prepared.

摘要翻译： 一种语音识别方法和装置，其中通过点样和候选词选择通过单词的单词切片语音部分。 接下来，在第二阶段中，通过音素单元进行匹配。 因此，可以同时执行候选词的选择和语音部分的切片。 此外，候选词的缩小变得容易。 此外，由于准备了多种环境下的参考音素模式，与在多种环境下的参考字模式被准备的情况相比，使用较少量的数据可以在更大数量的条件下识别输入语音 。

公开(公告)号：US5621849A

公开(公告)日：1997-04-15

申请号：US371494

申请日：1995-01-11

申请人： Atsushi Sakurai ,  Junichi Tamura ,  Tetsuo Kosaka ,  Hiroshi Matsuo

发明人： Atsushi Sakurai ,  Junichi Tamura ,  Tetsuo Kosaka ,  Hiroshi Matsuo

IPC分类号： G10L15/12 ,  G10L15/00 ,  G10L15/08 ,  G10L15/10 ,  G10L5/06 ,  G10L9/00

CPC分类号： G10L15/12 ,  G10L2015/088

摘要： A voice recognizing method apparatus in which an input voice is recognized by obtaining a similar pattern by comparing the input voice and voice standard patterns. Voice standard patterns are stored into a memory. A voice is inputted. Voice duration lengths and distances are calculated by performing matching processes between the input voice and the standard patterns. The distance is corrected in accordance with the voice duration length so that the voice duration length having the best matching result is used as a reference, or such that the distance is small as the voice duration length is long. A recognition result is determined in accordance with the corrected distance. The matching is executed by a word spotting method. The input voice to be matched and the voice standard patterns are expressed by voice characteristic parameters.

摘要翻译： 一种语音识别方法装置，其中通过比较输入的语音和语音标准模式来获得类似的模式来识别输入语音。 语音标准模式存储到存储器中。 输入声音。 通过执行输入语音和标准模式之间的匹配处理来计算语音持续时间长度和距离。 根据语音持续时间长度来校正距离，使得具有最佳匹配结果的语音持续时间长度被用作参考，或者使得距语音持续时间长度较短。 识别结果根据校正距离确定。 匹配是通过单词识别方法执行的。 要匹配的输入语音和语音标准模式由语音特征参数表示。

公开(公告)号：US5751898A

公开(公告)日：1998-05-12

申请号：US199968

申请日：1994-02-22

申请人： Tetsuo Kosaka ,  Atsushi Sakurai ,  Junichi Tamura

发明人： Tetsuo Kosaka ,  Atsushi Sakurai ,  Junichi Tamura

IPC分类号： G10L11/00 ,  G10L15/08 ,  G10L15/10 ,  G10L15/12 ,  G10L5/06

CPC分类号： G10L15/12 ,  G10L15/10

摘要： Speech recognition is achieved using a normalized cumulative distance. A normalized Dynamic Programming (DP) value is calculated by dividing a cumulative path distance by an optimal integral path length. The path length is calculated iteratively by adding 2 if the warping path is diagonal or by adding 3 if the warping path is horizontal or vertical. Distance may be calculated by measuring a difference between input power and average power. The power difference is weighted by a coefficient (.lambda.) between 0 and 1. A Mahalanobis distance is then weighted by (1-.lambda.) and added to the weighted power difference.

摘要翻译： 使用归一化的累积距离实现语音识别。 通过将累积路径距离除以最优积分路径长度来计算归一化动态规划（DP）值。 如果弯曲路径是对角线，则迭代地计算路径长度，如果弯曲路径是水平或垂直的，则通过加上2来计算路径长度。 距离可以通过测量输入功率和平均功率之间的差异来计算。 功率差由0和1之间的系数（λ）加权。然后通过（1-lambda）加权马哈拉诺比斯距离并将其加到加权功率差。

公开(公告)号：US5715363A

公开(公告)日：1998-02-03

申请号：US443791

申请日：1995-05-18

申请人： Junichi Tamura ,  Atsushi Sakurai ,  Tetsuo Kosaka

发明人： Junichi Tamura ,  Atsushi Sakurai ,  Tetsuo Kosaka

IPC分类号： G10L19/00 ,  G10L11/04 ,  G10L11/06 ,  G10L19/02 ,  G10L3/02

CPC分类号： G10L19/02 ,  G10L19/09 ,  G10L25/18 ,  G10L25/93

摘要： The speech processing apparatus and method includes a microphone, an analyzer, a selector, and a memory. The microphone converts input speech into an electrical signal representing speech data. The analyzer converts the speech data into non-linear frequency converted speech data in accordance with a non-linear frequency conversion. The selector selects a coefficient of the non-linear frequency conversion suitable for each of the phonemes or frames of the speech. The memory stores the speech data.

摘要翻译： 语音处理装置和方法包括麦克风，分析器，选择器和存储器。 麦克风将输入语音转换为表示语音数据的电信号。 分析仪根据非线性频率转换将语音数据转换为非线性变频语音数据。 选择器选择适合于语音的每个音素或帧的非线性频率转换的系数。 存储器存储语音数据。

公开(公告)号：US5369728A

公开(公告)日：1994-11-29

申请号：US895813

申请日：1992-06-09

申请人： Tetsuo Kosaka ,  Atsushi Sakurai ,  Junichi Tamura ,  Hiroshi Matsuo

发明人： Tetsuo Kosaka ,  Atsushi Sakurai ,  Junichi Tamura ,  Hiroshi Matsuo

IPC分类号： G10L15/06 ,  G10L15/00 ,  G10L15/08 ,  G10L15/10 ,  G10L15/20 ,  G10L9/00

CPC分类号： G10L15/10

摘要： An apparatus and method for recognizing speech includes a memory for storing data representing a reference pattern composed of the combination of a word reference pattern and a silence pattern, and a calculator for calculating the differences between data representing the reference pattern and data representing input speech. The use of such a silence pattern in the reference pattern permits a word such as "other" to be distinguished from the word "mother".

摘要翻译： 用于识别语音的装置和方法包括存储器，用于存储表示由字参考图案和静音图案的组合组成的参考图案的数据，以及用于计算表示参考图案的数据与表示输入语音的数据之间的差异的计算器。 在参考图案中使用这种沉默图案允许将诸如“其他”的单词与“母亲”一词区分开。

公开(公告)号：US5220629A

公开(公告)日：1993-06-15

申请号：US608757

申请日：1990-11-05

申请人： Tetsuo Kosaka ,  Atsushi Sakurai ,  Junichi Tamura ,  Yasunori Ohora ,  Takeshi Fujita ,  Takashi Aso ,  Katsuhiko Kawasaki

发明人： Tetsuo Kosaka ,  Atsushi Sakurai ,  Junichi Tamura ,  Yasunori Ohora ,  Takeshi Fujita ,  Takashi Aso ,  Katsuhiko Kawasaki

IPC分类号： G10L13/07

CPC分类号： G10L13/07

摘要： A method and apparatus for reading out a feature parameter and a driver sound source stored in a VCV (vowel-consonant-vowel) speech segment file, sequentially connecting the readout parameter and the readout sound source information in accordance with a predetermined rule, and supplying connected data to a speech synthesizer, thereby generating a speech output, includes a memory for storing the average power of each vowel, and a power controller for controlling the apparatus to normalize a VCV speech segment so that powers at both ends of each VCV segment coincide with the average power of each vowel.

公开(公告)号：US07058580B2

公开(公告)日：2006-06-06

申请号：US10956130

申请日：2004-10-04

申请人： Teruhiko Ueyama ,  Yasuhiro Komori ,  Tetsuo Kosaka ,  Masayuki Yamada ,  Akihiro Kushida

发明人： Teruhiko Ueyama ,  Yasuhiro Komori ,  Tetsuo Kosaka ,  Masayuki Yamada ,  Akihiro Kushida

IPC分类号： G10L15/04

CPC分类号： G10L15/30

摘要： The system implements high-accuracy speech recognition while suppressing the amount of data transfer between the client and server. For this purpose, the client compression-encodes speech parameters by a speech processing unit, and sends the compression-encoded speech parameters to the server. The server receives the compression-encoded speech parameters, a speech processing unit makes speech recognition of the compression-encoded speech parameters, and sends information corresponding to the speech recognition result to the client.

摘要翻译： 系统实现高精度语音识别，同时抑制客户端与服务器之间的数据传输量。 为此，客户机通过语音处理单元对语音参数进行压缩编码，并将压缩编码的语音参数发送到服务器。 服务器接收压缩编码的语音参数，语音处理单元进行压缩编码语音参数的语音识别，并将与语音识别结果相对应的信息发送给客户端。

公开(公告)号：US20050119888A1

公开(公告)日：2005-06-02

申请号：US10497499

申请日：2002-12-10

申请人： Keiichi Sakai ,  Tetsuo Kosaka

发明人： Keiichi Sakai ,  Tetsuo Kosaka

IPC分类号： G06F3/16 ,  G06F3/033 ,  G06F3/048 ,  G09G5/34 ,  G10L13/00 ,  G10L13/04 ,  G10L21/06

CPC分类号： G06F3/0481 ,  G06F3/16 ,  G09G5/34 ,  G10L13/00

摘要： A GUI display module displays a contents image based on contents data within a display area, and a display portion switching input module instructs to change the display portion of the contents image within the display area. Based on this instruction input, a display portion switching module changes the display portion of the contents image within the display area. A synthesis text determination module determines data which is to undergo speech synthesis in the contents data on the basis of display portion information which is held by a display portion holding module and indicates the display portion. A speech synthesis module synthesizes speech of the data which is to undergo speech synthesis, and a speech output module outputs the synthesized synthetic speech.

摘要翻译： GUI显示模块基于显示区域内的内容数据显示内容图像，并且显示部分切换输入模块指示改变显示区域内的内容图像的显示部分。 基于该指令输入，显示部分切换模块改变显示区域内的内容图像的显示部分。 合成文本确定模块基于由显示部分保持模块保持并指示显示部分的显示部分信息来确定要在内容数据中进行语音合成的数据。 语音合成模块合成要进行语音合成的数据的语音，并且语音输出模块输出合成的合成语音。

公开(公告)号：US5893058A

公开(公告)日：1999-04-06

申请号：US340468

申请日：1994-11-14

申请人： Tetsuo Kosaka

发明人： Tetsuo Kosaka

IPC分类号： G06F3/16 ,  G10L15/02 ,  G10L15/08 ,  G10L15/10 ,  G10L15/12 ,  G10L15/14 ,  G10L15/16 ,  G10L15/28 ,  G10L5/00

CPC分类号： G10L15/12 ,  G10L15/16 ,  G10L15/32 ,  G10L15/142

摘要： A method and apparatus for recognizing speech employing a word dictionary in which the phoneme of words are stored and for recognizing speech based on the recognition of the phonemes. The method and apparatus recognize phonemes and produce data associated with each phoneme according to different speech analyzing and recognizing methods for each kind of phoneme, normalize the produced data, and match the recognized phonemes with words in the word dictionary by means of dynamic programming based on the normalized data.

摘要翻译： 用于识别语音的方法和装置，该语音采用其中存储字母的音素的词典，并且用于基于音素的识别来识别语音。 该方法和装置根据每种音素的不同语音分析和识别方法识别音素并产生与每个音素相关的数据，对所产生的数据进行归一化，并通过基于以下的动态规划，将识别的音素与词典中的单词相匹配： 归一化数据。