专利快速检索-快速检索全球专利，免费商用专利数据库-IPRDB

1. 发明专利

JP2015060002A 韻律編集装置、方法およびプログラム有权
标题翻译： RHYTHM处理系统及方法与程序
公开(公告)号：JP2015060002A
公开(公告)日：2015-03-30
申请号：JP2013192359
申请日：2013-09-17
申请人：株式会社東芝 , Toshiba Corp
发明人： MORI KOICHIRO , NASU YU , TAMURA MASANORI , MORITA SHINKO
IPC分类号： G10L13/10
CPC分类号： G10L13/033 , G10L13/10
摘要：【課題】直感的かつ簡便な操作でユーザが望む自然な韻律を得ることができる韻律編集装置、方法およびプログラムを提供する。【解決手段】実施形態の韻律編集装置100は、生成部102と、設定部103と、表示制御部104と、操作受付部105と、更新部106と、を備える。生成部102は、韻律情報の時系列を表す軌跡を所定単位ごとにパラメトリック曲線により近似し、近似軌跡を生成する。設定部103は、前記パラメトリック曲線の制御点に対応する操作点を前記近似軌跡上に設定する。表示制御部104は、前記操作点を明示した前記近似軌跡を含む操作画面を表示装置120に表示させる。操作受付部105は、前記操作画面上で任意の前記操作点を移動させる操作を受け付ける。更新部106は、前記操作点の移動量から移動後の該操作点に対応する前記制御点の位置を求め、前記近似軌跡を更新する。【選択図】図1
摘要翻译：要解决的问题：提供能够以直观且简单的操作获得用户所期望的自然节奏的节奏处理系统，方法和程序。解决方案：节奏处理系统100包括：生成部分102; 设定部103; 显示控制部104; 操作接收部105; 和更新部分106.生成部分102使用参数曲线近似表示每个预定单位的节奏信息的时间序列转变的轨迹，以生成近似轨迹。设定部103设定与近似轨迹的参数曲线上的控制点对应的动作点。显示控制部分104控制显示装置120显示包括具有设定操作点的近似轨迹的操作屏幕。操作接收部105接收在操作画面上移动期望的操作点的动作。更新部106基于操作点的移动量计算与移动的操作点对应的控制点的位置，并更新近似轨迹。

2. 发明专利

JP2010049196A Voice conversion apparatus and method, and speech synthesis apparatus and method 有权
标题翻译：语音转换装置和方法，以及语音合成装置和方法
公开(公告)号：JP2010049196A
公开(公告)日：2010-03-04
申请号：JP2008215711
申请日：2008-08-25
申请人： Toshiba Corp , 株式会社東芝
发明人： TAMURA MASANORI , MORITA SHINKO , KAGOSHIMA TAKEHIKO
IPC分类号： G10L21/04
CPC分类号： G10L13/033 , G10L2021/0135
摘要： PROBLEM TO BE SOLVED: To provide a voice conversion method and apparatus, capable of easily creating voice with high quality having voice quality of target speech, from a small amount of target speech. SOLUTION: A source speech spectrum parameter for expressing characteristics of voice quality is extracted from input source speech. The source speech parameter is converted to a first conversion spectrum parameter by using a voice quality conversion rule (which is a rule for converting the voice quality of the source speech, to the voice quality of the target speech). A target speech spectrum parameter which is similar to the first conversion spectrum parameter is selected, from a plurality of target speech spectrum parameters stored in a storage means. An aperiodic component spectrum parameter for expressing an aperiodic parameter of the voice quality is created from the selected target speech spectrum parameter. A second conversion spectrum parameter is created by mixing a periodic component spectrum parameter with the aperiodic component spectrum parameter for expressing a periodic component of the voice quality included in the first conversion spectrum parameter. COPYRIGHT: (C)2010,JPO&INPIT
摘要翻译：要解决的问题：提供一种语音转换方法和装置，能够从少量的目标语音容易地创建具有目标语音的语音质量的高质量的语音。解决方案：从输入源语音中提取用于表达语音质量特征的源语音频谱参数。通过使用语音质量转换规则（其是用于将源语音的语音质量转换为目标语音的语音质量的规则）将源语音参数转换为第一转换频谱参数。从存储在存储装置中的多个目标语音频谱参数中选择类似于第一转换频谱参数的目标语音频谱参数。从所选择的目标语音频谱参数创建用于表达语音质量的非周期参数的非周期分量频谱参数。通过将周期性分量频谱参数与非周期分量频谱参数混合以产生包括在第一转换频谱参数中的语音质量的周期分量来创建第二转换频谱参数。版权所有（C）2010，JPO＆INPIT

3. 发明专利

JP2006276528A Voice synthesizer and method thereof 有权
标题翻译：语音合成器及其方法
公开(公告)号：JP2006276528A
公开(公告)日：2006-10-12
申请号：JP2005096526
申请日：2005-03-29
申请人： Toshiba Corp , 株式会社東芝
发明人： TAMURA MASANORI , HIRABAYASHI TAKESHI , KAGOSHIMA TAKEHIKO
IPC分类号： G10L13/06 , G10L13/08
CPC分类号： G10L13/07
摘要： PROBLEM TO BE SOLVED: To provide a high quality voice synthesizer by which power information of a large-scale voice element is appropriately reflected and pieces of power information of voice elements in each voice section become natural and stable one in voice synthesis of an element selection type or a multiple element selection type. SOLUTION: A voice synthesis part 14 is constituted of a voice element storage part 21, a phonemic environment storage part 22, a phonological sequence/prosodic information input part 23, a multiple voice element selection part 24, a fused voice element sequence creation part 25 and a fused voice element editing/connection part 26, and generates the fused voice element by fusing the plurality of selected elements in the fused voice element sequence creation part 25. In the fused voice element sequence creation part 25, average power information about a plurality of the selected M voice elements is calculated, N voice elements are fused and power information of the generated fused voice elements is corrected so that it becomes the average power information of the M voice elements. COPYRIGHT: (C)2007,JPO&INPIT
摘要翻译：要解决的问题：提供一种高质量的语音合成器，通过该高质量语音合成器，大规模语音元素的功率信息被适当地反映，并且每个语音部分中的语音元素的功率信息的片段在语音合成中变得自然而稳定元素选择类型或多元素选择类型。解决方案：语音合成部分14由语音元素存储部分21，音素环境存储部分22，语音序列/韵律信息输入部分23，多声音元素选择部分24，融合语音元素序列创建部分25和融合语音元素编辑/连接部分26，并且通过融合融合语音元素序列创建部分25中的多个所选择的元素来生成融合语音元素。在融合语音元素序列创建部分25中，平均功率信息计算多个所选择的M个语音元素，N个语音元素被融合，并且校正所生成的融合语音元素的功率信息，使其成为M个语音元素的平均功率信息。版权所有（C）2007，JPO＆INPIT

4. 发明专利

JP2013171196A Device, method and program for voice synthesis 有权
标题翻译：语音合成的设备，方法和程序
公开(公告)号：JP2013171196A
公开(公告)日：2013-09-02
申请号：JP2012035520
申请日：2012-02-21
申请人： Toshiba Corp , 株式会社東芝
发明人： TAMURA MASANORI , MORITA SHINKO
IPC分类号： G10L13/06 , G10L13/07 , G10L13/10
CPC分类号： G10L13/08 , G10L13/033 , G10L13/06
摘要： PROBLEM TO BE SOLVED: To provide a voice synthesis device, which can increase similarity to a target utterance voice.SOLUTION: The voice synthesis device includes a conversion source voice data storage part (second storage part) 11, a target voice data storage part (first storage part) 12, a voice data conversion part (first generation part) 13, a voice data set generation part (second generation part) 14, a voice synthesis data generation part (third generation part) 15, a voice synthesis data storage part 20, and a voice synthesis part (fourth generation part) 16. The first storage part stores first information obtained from a target utterance voice. The second storage part stores second information obtained from an arbitrary utterance voice. The first generation part converts the second information so that it can become close to a target voice quality or rhythm, so as to generate third information. The second generation part generates information set including the first information and the third information. The third generation part generates, on the basis of the information set, fourth information used for generating a synthesized voice. The fourth generation part generates, while using the fourth information, a synthesized voice corresponding to an input text.
摘要翻译：要解决的问题：提供一种语音合成装置，其可以增加与目标语音语音的相似度。解决方案：语音合成装置包括转换源语音数据存储部分（第二存储部分）11，目标语音数据存储部分第一存储部分）12，语音数据转换部分（第一代部分）13，语音数据集生成部分（第二生成部分）14，语音合成数据生成部分（第三代部分）15，语音合成数据存储部分 20，以及语音合成部（第四代部）16。第一存储部存储从目标话音语音获得的第一信息。第二存储部分存储从任意话音语音获得的第二信息。第一代部分将第二信息转换成接近目标语音质量或节奏，从而产生第三信息。第二代部分生成包括第一信息和第三信息的信息集。第三代部分基于信息集合生成用于产生合成语音的第四信息。第四代部分在使用第四信息时产生与输入文本相对应的合成语音。

5. 发明专利

JP2009139406A Speech processing device, and speech synthesis device using it 有权
标题翻译：语音处理设备和使用它的语音合成设备
公开(公告)号：JP2009139406A
公开(公告)日：2009-06-25
申请号：JP2007312336
申请日：2007-12-03
申请人： Toshiba Corp , 株式会社東芝
发明人： TAMURA MASANORI , TSUCHIYA KATSUMI , KAGOSHIMA TAKEHIKO
IPC分类号： G10L13/06 , G10L11/00 , G10L13/02
CPC分类号： G10L13/06
摘要： PROBLEM TO BE SOLVED: To provide a speech processing device capable of easily performing a high-quality and efficient process according to a range by modeling a logarithm spectral envelope as a linear combination of a local basis. SOLUTION: This speech processing device includes a speech frame extraction part 11 which divides speech data into speech frames, an envelope extraction part 12 which extracts a logarithm spectral envelope from the obtained speech frame, a local base creation part 14 which creates a local base, a local base holding part 15 which holds the local base, and a parameter calculation part 13 which determines a spectral envelope parameter from the logarithm spectral envelope using the held local base. COPYRIGHT: (C)2009,JPO&INPIT
摘要翻译：要解决的问题：提供一种语音处理装置，其能够通过将对数频谱包络建模为局部基础的线性组合，来容易地根据范围执行高质量和有效的处理。解决方案：该语音处理装置包括将语音数据划分成语音帧的语音帧提取部分11，从获得的语音帧中提取对数频谱包络的包络提取部分12，其创建一个本地基座，保持本地基座的本地基座保持部分15，以及参数计算部分13，其使用保持的本地基线从对数频谱包络线确定频谱包络参数。版权所有（C）2009，JPO＆INPIT

6. 发明专利

JP2007193139A Voice processing device and method therefor 有权
标题翻译：语音处理设备及其方法
公开(公告)号：JP2007193139A
公开(公告)日：2007-08-02
申请号：JP2006011653
申请日：2006-01-19
申请人： Toshiba Corp , 株式会社東芝
发明人： TAMURA MASANORI , KAGOSHIMA TAKEHIKO
IPC分类号： G10L21/04 , G10L13/08
CPC分类号： G10L13/033 , G10L2021/0135
摘要： PROBLEM TO BE SOLVED: To provide a voice quality conversion rule creation device permitting to create a voice quality conversion rule by phonation of an arbitrary sentence by a target speaker for conversion. SOLUTION: The voice quality conversion rule creation device comprises a converted speaker voice element database 11, a voice quality conversion rule learning data creation part 12, and a voice quality conversion rule learning part 13 and creates the voice quality conversion rule 14; the voice quality conversion rule learning data creation part 12 is constituted of a voice elementary unit extraction part 21 of the target speaker for conversion, an attribute creation part 22, the converted speaker voice elementary unit database 11, and a converted speaker voice elementary unit selection part 23; the converted speaker voice elementary unit selection part 23 selects the converted speaker voice elementary units corresponding to the target speaker voice elementary units based on distortion by attribute information of the converted speaker voice elementary units and that of converted speaker voice elementary units; and the voice quality conversion rule 14 is created from pairs of the target speaker voice elementary units and the converted speaker voice elementary units selected in this way. COPYRIGHT: (C)2007,JPO&INPIT
摘要翻译：要解决的问题：提供语音质量转换规则创建装置，允许通过目标扬声器通过任意句子的发音创建语音质量转换规则以进行转换。语音质量转换规则创建装置包括转换的扬声器语音元素数据库11，语音质量转换规则学习数据创建部分12和语音质量转换规则学习部分13，并创建语音质量转换规则14; 语音质量转换规则学习数据创建部分12由目标讲话者的转换语音基本单元提取部分21，属性创建部分22，转换的说话者话音基本单元数据库11和转换的说话者话音单元选择第23部分; 转换后的说话者语音基本单元选择部23基于通过转换的说话者语音基本单元的属性信息和转换的说话者语音单元单位的属性信息，选择与目标讲话者语音单元对应的转换语音基本单元; 并且语音质量转换规则14是由目标扬声器语音基本单元和以这种方式选择的经转换的扬声器语音单元单元的对创建的。版权所有（C）2007，JPO＆INPIT

7. 发明专利

JP2005292433A Device, method, and program for speech synthesis 有权
标题翻译：语音合成的设备，方法和程序
公开(公告)号：JP2005292433A
公开(公告)日：2005-10-20
申请号：JP2004106711
申请日：2004-03-31
申请人： Toshiba Corp , 株式会社東芝
发明人： TAMURA MASANORI , MIZUTANI TATSUYA , KAGOSHIMA TAKEHIKO , TSUCHIYA KATSUMI
IPC分类号： G10L13/08 , G10L13/06
摘要： PROBLEM TO BE SOLVED: To provide a speech synthesizer efficiently synthesizing a natural speech of high quality. SOLUTION: The speech synthesizer is provided with: an acquiring means 110 of acquiring a meter series for a target speech to be synthesized for a plurality of segments respectively; merged speech element holding means 160 and 170 of holding merged speech elements obtained by merging a plurality of speech elements and merged speech element meter information showing meters of the merged speech elements while making them correspond to each other; a held speech distortion estimating means 130 of estimating the degree of distortion between segment meter information showing meters of segments obtained by the acquiring means 110 and the merged speech element meter information held in the merged speech element holding means 160 and 170; a merged speech element selecting means 140 of selecting a merged speech element on the basis of the degree of distortion estimated by the held speech distortion estimating means 130; and a speech synthesizing means 150 of generating a synthesized speech by connecting respective merged speech elements that the merged speech element selecting means 140 select for the respective segments. COPYRIGHT: (C)2006,JPO&NCIPI
摘要翻译：要解决的问题：提供一种高效地合成高质量自然语音的语音合成器。解决方案：语音合成器具有：获取装置110，用于分别为多个频段获取要合成的目标话音的音调序列; 通过合并多个语音元素而获得的合并语音元素的合并语音元素保持单元160和170，以及表示合并语音单元的米的合并语音单元表信息，同时使彼此对应; 保持语音失真估计装置130，用于估计表示由获取装置110获得的片段的片段的片段计量信息与合并的语音元素保持装置160和170中保存的合并语音元素计量信息之间的失真程度; 合并语音元素选择单元140，根据被保持语音失真估计单元130所估计的失真程度选择合并语音单元; 以及语音合成装置150，其通过连接合并的语音元素选择装置140为各个段选择的各个合并语音元素来生成合成语音。版权所有（C）2006，JPO＆NCIPI

8. 发明专利

JP2014174278A Voice synthesis dictionary editing device, voice synthesis dictionary editing method, and voice synthesis dictionary editing program 有权
标题翻译：语音合成字典编辑设备，语音合成字典编辑方法和语音合成字典编辑程序
公开(公告)号：JP2014174278A
公开(公告)日：2014-09-22
申请号：JP2013045757
申请日：2013-03-07
申请人： Toshiba Corp , 株式会社東芝
发明人： MORINAKA RYO , TAMURA MASANORI , MORITA SHINKO
IPC分类号： G10L13/06
CPC分类号： G10L13/02
摘要： PROBLEM TO BE SOLVED: To provide a voice synthesis dictionary editing device, a voice synthesis dictionary editing method, and a voice synthesis dictionary editing program capable of efficiently improving the quality of a voice synthesis dictionary.SOLUTION: The voice synthesis dictionary editing device has an extraction part, display part, an acquisition part, an editing part, and an update part. The extraction part extracts synthesis information including a feature quantity sequence from synthetic voice generated by using a voice synthesis dictionary including a probability distribution of a voice feature quantity. The display part displays a screen which prompts a user to edit the probability distribution included in the voice synthesis dictionary on the basis of the synthesis information extracted by the extraction part. The acquisition part receives an instruction to edit the probability distribution included in the voice synthesis dictionary. The editing part edits the probability distribution included in the voice synthesis dictionary, following the instruction. The update part updates the voice synthesis dictionary on the basis of a result of the edition by the editing part so as to newly generate a voice synthesis dictionary.
摘要翻译：要解决的问题：提供能够有效提高语音合成词典的质量的语音合成词典编辑装置，语音合成词典编辑方法和语音合成词典编辑程序。解码：语音合成词典编辑装置具有提取部分，显示部分，获取部分，编辑部分和更新部分。提取部分提取包括通过使用包括语音特征量的概率分布的语音合成词典产生的合成语音的特征量序列的合成信息。显示部显示提示用户根据由提取部提取的合成信息来编辑语音合成词典中包含的概率分布的画面。获取部分接收编辑语音合成词典中包含的概率分布的指令。编辑部分按照说明编辑语音合成词典中包含的概率分布。更新部分基于编辑部分的编辑结果来更新语音合成词典，以便新生成语音合成词典。

9. 发明专利

JP2012048154A Voice synthesizer, voice synthesizing method and program 有权
标题翻译：语音合成器，语音合成方法和程序
公开(公告)号：JP2012048154A
公开(公告)日：2012-03-08
申请号：JP2010192656
申请日：2010-08-30
申请人： Toshiba Corp , 株式会社東芝
发明人： TAMURA MASANORI , MORITA SHINKO , KAGOSHIMA TAKEHIKO
IPC分类号： G10L13/08 , G10L13/06
CPC分类号： G10L13/04 , G10L25/18
摘要： PROBLEM TO BE SOLVED: To generate a speech waveform at a high speed.SOLUTION: A first storage part stores n band noise signals obtained by applying n band pass filters to a noise signal. A second storage part stores n band pulse signals obtained by applying the n band pass filters to a pulse signal. A parameter input unit inputs a fundamental frequency, n band noise intensities, and a spectrum parameter. An extraction section extracts the n band noise signals while shifting them for each pitch mark. An amplitude control part changes the amplitude of an extracted band noise signal and the amplitude of the band pulse signal according to the band noise intensity. A generation part generates mixed sound source signals obtained by adding the n band noise signals and the n band pulse signals. A superimposition part superimposes the mixed sound source signals generated based on the pitch mark. A vocal tract filter part generates speech waveforms by applying the vocal tract filter using the spectrum parameter to the superimposed mixed sound source signals.
摘要翻译：要解决的问题：高速产生语音波形。解决方案：第一存储部件存储通过将n个带通滤波器应用于噪声信号而获得的n个带噪声信号。第二存储部件将通过将n个带通滤波器应用得到的n个带脉冲信号存储到脉冲信号。参数输入单元输入基频，n频带噪声强度和频谱参数。提取部分提取n个带噪声信号，同时为每个音调标记移位它们。幅度控制部分根据带噪声强度改变提取的频带噪声信号的幅度和频带脉冲信号的幅度。一代部生成通过相加n个带噪声信号和n个带脉冲信号而获得的混合声源信号。叠加部分叠加基于间距标记产生的混合声源信号。声道滤波器部分通过使用频谱参数将声道滤波器应用于叠加的混合声源信号来产生语音波形。版权所有（C）2012，JPO＆INPIT

10. 发明专利

JP2013205697A Speech synthesizer, speech synthesis method, speech synthesis program and learning device 有权
标题翻译：语音合成器，语音合成方法，语音合成程序和学习设备
公开(公告)号：JP2013205697A
公开(公告)日：2013-10-07
申请号：JP2012075967
申请日：2012-03-29
申请人： Toshiba Corp , 株式会社東芝
发明人： OTANI YAMATO , TAMURA MASANORI , MORITA SHINKO
IPC分类号： G10L13/02 , G10L13/08 , G10L13/10 , G10L25/03 , G10L25/06
CPC分类号： G06F17/28 , G10L13/02
摘要： PROBLEM TO BE SOLVED: To improve quality of a synthesized speech.SOLUTION: A speech synthesizer comprises: a language analysis part for outputting language information data showing linguistic information, by analyzing text data; a statistical model holding part for holding multiple statistical models obtained by statistically modeling acoustic information included in a speech; a model selection part for selecting any one of the statistical models on the basis of the language information data; a parameter generation part for using the statistical model selected in the model selection part to generate multiple speech parameter sequences; a base model holding part for holding a base model including multiple base vectors that respectively express information for the speech per limited bandwidth; and a filter processing part for outputting a synthesized speech by applying filter processing to the speech parameter sequences and to the base model.
摘要翻译：要解决的问题：提高合成语音的质量。解决方案：语音合成器包括：语言分析部分，用于通过分析文本数据来输出表示语言信息的语言信息数据; 统计模型保持部分，用于保持通过统计建模包括在语音中的声学信息获得的多个统计模型; 模型选择部分，用于基于语言信息数据选择任一个统计模型; 用于使用在模型选择部分中选择的统计模型来生成多个语音参数序列的参数生成部分; 用于保持包含多个基本向量的基本模型的基本模型保持部分，其分别在每个有限带宽上表示所述语音的信息; 以及滤波处理部分，用于通过对语音参数序列和基本模型应用滤波处理来输出合成语音。

你已经成功收藏专利！

检索式保存成功!

IPRDB

热门服务

关于我们

友情链接

联系方式