公开(公告)号：US08438033B2

公开(公告)日：2013-05-07

申请号：US12505684

申请日：2009-07-20

Applicant: Masatsune Tamura ,  Masahiro Morita ,  Takehiko Kagoshima

Inventor： Masatsune Tamura ,  Masahiro Morita ,  Takehiko Kagoshima

IPC: G10L13/06 ,  G10L13/00 ,  G10L21/00

CPC classification number: G10L13/033 ,  G10L2021/0135

Abstract: A voice conversion apparatus stores, in a parameter memory, target speech spectral parameters of target speech, stores, in a voice conversion rule memory, a voice conversion rule for converting voice quality of source speech into voice quality of the target speech, extracts, from an input source speech, a source speech spectral parameter of the input source speech, converts extracted source speech spectral parameter into a first conversion spectral parameter by using the voice conversion rule, selects target speech spectral parameter similar to the first conversion spectral parameter from the parameter memory, generates an aperiodic component spectral parameter representing from selected target speech spectral parameter, mixes a periodic component spectral parameter included in the first conversion spectral parameter with the aperiodic component spectral parameter, to obtain a second conversion spectral parameter, and generates a speech waveform from the second conversion spectral parameter.

Abstract translation: 语音转换装置在参数存储器中存储目标语音的目标语音频谱参数，在语音转换规则存储器中存储用于将源语音的语音质量转换为目标语音的语音质量的语音转换规则，从 输入源语音，输入源语音的源语音频谱参数通过使用语音转换规则将提取的源语音频谱参数转换为第一转换频谱参数，从参数中选择类似于第一转换谱参数的目标语音频谱参数 生成从选定的目标语音频谱参数表示的非周期分量谱参数，将包含在第一转换频谱参数中的周期分量频谱参数与非周期分量频谱参数进行混合，得到第二转换频谱参数，并从 第二个转换光谱第 仪表。

公开(公告)号：US20120259630A1

公开(公告)日：2012-10-11

申请号：US13444190

申请日：2012-04-11

Applicant: Aditi GARG ,  Kasthuri Jayachand YADLAPALLI

Inventor： Aditi GARG ,  Kasthuri Jayachand YADLAPALLI

IPC: G10L15/20

CPC classification number: G10L13/033 ,  G10L2021/0135

Abstract: The voice conversion method of a display apparatus includes: in response to the receipt of a first video frame, detecting one or more entities from the first video frame; in response to the selection of one of the detected entities, storing the selected entity; in response to the selection of one of a plurality of previously-stored voice samples, storing the selected voice sample in connection with the selected entity; and in response to the receipt of a second video frame including the selected entity, changing a voice of the selected entity based on the selected voice sample and outputting the changed voice.

Abstract translation: 显示装置的语音转换方法包括：响应于接收到第一视频帧，从第一视频帧中检测一个或多个实体; 响应于所检测到的一个实体的选择，存储所选择的实体; 响应于选择多个先前存储的语音样本中的一个语音样本，与所选择的实体相关联存储所选择的语音样本; 并且响应于接收到包括所选择的实体的第二视频帧，基于所选择的语音样本改变所选择的实体的语音并输出改变的语音。

公开(公告)号：US08224648B2

公开(公告)日：2012-07-17

申请号：US11966255

申请日：2007-12-28

Applicant: Jilei Tian ,  Victor Popa ,  Jani Kristian Nurminen

Inventor： Jilei Tian ,  Victor Popa ,  Jani Kristian Nurminen

IPC: G01L13/06

CPC classification number: G10L21/00 ,  G10L2021/0135

Abstract: A hybrid approach is described for combining frequency warping and Gaussian Mixture Modeling (GMM) to achieve better speaker identity and speech quality. To train the voice conversion GMM model, line spectral frequency and other features are extracted from a set of source sounds to generate a source feature vector and from a set of target sounds to generate a target feature vector. The GMM model is estimated based on the aligned source feature vector and the target feature vector. A mixture specific warping function is generated each set of mixture mean pairs of the GMM model, and a warping function is generated based on a weighting of each of the mixture specific warping functions. The warping function can be used to convert sounds received from a source speaker to approximate speech of a target speaker.

Abstract translation: 描述了混合方法，用于组合频率扭曲和高斯混合建模（GMM），以实现更好的扬声器身份和语音质量。 为了训练语音转换GMM模型，从一组源声音中提取线谱频率和其他特征以产生源特征向量和从一组目标声音生成目标特征向量。 基于对齐的源特征向量和目标特征向量来估计GMM模型。 每个GMM模型的混合均值对都产生混合特定的翘曲函数，并且基于每个混合特定翘曲函数的加权产生翘曲函数。 翘曲功能可用于将从源扬声器接收的声音转换为目标扬声器的近似语音。

公开(公告)号：US20120095767A1

公开(公告)日：2012-04-19

申请号：US13334119

申请日：2011-12-22

Applicant: Yoshifumi HIROSE ,  Takahiro Kamai

Inventor： Yoshifumi HIROSE ,  Takahiro Kamai

IPC: G10L13/00

CPC classification number: G10L13/033 ,  G10L2021/0135

Abstract: A device includes: an input speech separation unit which separates an input speech into vocal tract information and voicing source information; a mouth opening degree calculation unit which calculates a mouth opening degree from the vocal tract information; a target vowel database storage unit which stores pieces of vowel information on a target speaker; an agreement degree calculation unit which calculates a degree of agreement between the calculated mouth opening degree and a mouth opening degree included in the vowel information; a target vowel selection unit which selects the vowel information from among the pieces of vowel information, based on the calculated agreement degree; a vowel transformation unit which transforms the vocal tract information on the input speech, using vocal tract information included in the selected vowel information; and a synthesis unit which generates a synthetic speech using the transformed vocal tract information and the voicing source information.

Abstract translation: 一种设备包括：输入语音分离单元，其将输入语音分离成声道信息和发声源信息; 嘴开度计算单元，从声道信息计算开口度; 目标元音数据库存储单元，其在目标说话者上存储元音信息; 协调度计算单元，计算计算出的开口程度与包含在元音信息中的开口度之间的一致程度; 目标元音选择单元，根据计算出的协议程度从元音信息中选出元音信息; 元音变换单元，其使用包括在所选择的元音信息中的声道信息来变换输入语音的声道信息; 以及合成单元，其使用变换的声道信息和发声源信息来生成合成语音。

公开(公告)号：US08131550B2

公开(公告)日：2012-03-06

申请号：US11867033

申请日：2007-10-04

Applicant: Jani Nurminen ,  Elina Helander

Inventor： Jani Nurminen ,  Elina Helander

IPC: G10L13/00

CPC classification number: G10L13/033 ,  G10L2021/0135

Abstract: An apparatus for providing improved voice conversion includes a sub-feature generator and a transformation element. The sub-feature generator may be configured to define sub-feature units with respect to a feature of source speech. The transformation element may be configured to perform voice conversion of the source speech to target speech based on the conversion of the sub-feature units to corresponding target speech sub-feature units using a conversion model trained with respect to converting training source speech sub-feature units to training target speech sub-feature units.

Abstract translation: 用于提供改进的语音转换的装置包括子特征生成器和变换元件。 子特征生成器可以被配置为相对于源语音的特征定义子特征单元。 转换元件可以被配置为基于使用针对转换训练源语音子特征而训练的转换模型，将子特征单元转换为对应的目标语音子特征单元来执行源语音到目标语音的语音转换 单位训练目标语音子特征单位。

公开(公告)号：US08131549B2

公开(公告)日：2012-03-06

申请号：US11752989

申请日：2007-05-24

Applicant: Hugh A. Teegan ,  Eric N. Badger ,  Drew E. Linerud

Inventor： Hugh A. Teegan ,  Eric N. Badger ,  Drew E. Linerud

IPC: G10L13/08

CPC classification number: G10L13/033 ,  G10L2021/0135

Abstract: A personality-based theme may be provided to a device. An application program may query a personality resource file for a prompt corresponding to a personality. Then the prompt may be received at a text to speech synthesis engine. Next, the speech synthesis engine may query a personality voice font and recorded phrases database for a voice font corresponding to the personality and may alter the prompt text to conform with the grammatical style of the personality. Then the speech synthesis engine may apply the voice font to the prompt, which is then produced at an output device.

Abstract translation: 可以向设备提供基于个性的主题。 应用程序可以查询个性资源文件以获得与个性相对应的提示。 然后可以在文本到语音合成引擎处接收提示。 接下来，语音合成引擎可以查询与个性对应的语音字体的个性语音字体和记录的短语数据库，并且可以改变提示文本以符合个性的语法风格。 然后，语音合成引擎可以将语音字体应用于提示，然后在输出设备处产生。

公开(公告)号：US08123615B2

公开(公告)日：2012-02-28

申请号：US12358957

申请日：2009-01-23

Applicant: Kazuo Okada

Inventor： Kazuo Okada

IPC: A63F9/24 ,  A63F13/00 ,  G06F17/00 ,  G06F19/00

CPC classification number: G07F17/3216 ,  A63F2300/1081 ,  A63F2300/8023 ,  G07F17/3209 ,  G07F17/3211 ,  G07F17/3227 ,  G07F17/3232 ,  G07F17/3272 ,  G10L13/033 ,  G10L2021/0135

Abstract: Herein disclosed is a gaming machine executing a game and paying out a predetermined amount of credits according to a game result; generating voice data based on a player's voice; identifying a voice pattern corresponding to the voice data by retrieving the dialogue voice database and identifying a type of voice corresponding to the voice data, so as to store the voice data along with the voice pattern into the memory; calculating a value indicative of a game result, and updating the play history data stored in the memory using the result of the calculation; comparing the play history data thus updated with a predetermined threshold value data; generating voice data according to the voice pattern based on the play history data if the play history data thus updated exceeds the predetermined threshold value data; and outputting voices from the speaker.

Abstract translation: 这里公开的是游戏机，其执行游戏并根据游戏结果支付预定量的信用; 基于玩家的声音产生语音数据; 通过检索对话语音数据库和识别对应于语音数据的语音类型来识别与语音数据相对应的语音模式，以便将语音数据与语音模式一起存储到存储器中; 计算指示游戏结果的值，并使用计算结果更新存储在存储器中的播放历史数据; 将由此更新的播放历史数据与预定阈值数据进行比较; 如果这样更新的播放历史数据超过预定阈值数据，则根据播放历史数据根据语音模式生成语音数据; 并从扬声器输出语音。

公开(公告)号：US20110313759A1

公开(公告)日：2011-12-22

申请号：US13162003

申请日：2011-06-16

Applicant: Alon Konchitsky

Inventor： Alon Konchitsky

IPC: G10L21/00

CPC classification number: G10L13/02 ,  G10L25/90 ,  G10L2021/0135

Abstract: The invention relates to a cellular phone terminal system and in particular to a method for changing caller's voice of speech signal during conversation. The cellular phone terminal system has a filter for filtering signal. The method comprises the steps of: waiting for a caller voice selector key input for a desired caller voice when a caller voice converter key is pressed during conversation; and setting an even or odd harmonic deletion bins on the frequency domain of the uncompressed speech signal correspondingly to the caller voice selector key input to change caller voice.

Abstract translation: 本发明涉及一种蜂窝电话终端系统，尤其涉及一种用于在对话期间改变呼叫者语音信号语音的方法。 蜂窝电话终端系统具有用于过滤信号的滤波器。 该方法包括以下步骤：当在对话期间按下呼叫者语音转换器键时，等待呼叫者语音选择器键输入所需呼叫者语音; 以及对应于呼叫者语音选择器键输入，在未压缩语音信号的频域上设置偶数或奇数的谐波删除箱，以改变呼叫者语音。

公开(公告)号：US08073688B2

公开(公告)日：2011-12-06

申请号：US11165695

申请日：2005-06-24

Applicant: Yasuo Yoshioka ,  Alex Loscos

Inventor： Yasuo Yoshioka ,  Alex Loscos

IPC: G10L19/14

CPC classification number: G10L13/033 ,  G10L2021/0135

Abstract: Envelope identification section generates input envelope data (DEVin) indicative of a spectral envelope (EVin) of an input voice. Template acquisition section reads out, from a storage section, converting spectrum data (DSPt) indicative of a frequency spectrum (SPt) of a converting voice. On the basis of the input envelope data (DEVin) and the converting spectrum data (DSPt), a data generation section specifies a frequency spectrum (SPnew) corresponding in shape to the frequency spectrum (SPt) of the converting voice and having a substantially same spectral envelope as the spectral envelope (EVin) of the input voice, and the data generation section generates new spectrum data (DSPnew) indicative of the frequency spectrum (SPnew). Reverse FFT section and output processing section generates an output voice signal (Snew) on the basis of the new spectrum data (DSPnew).

Abstract translation: 信封识别部分生成表示输入声音的频谱包络（EVin）的输入包络数据（DEVin）。 模板获取部从存储部读出表示转换语音的频谱（SPt）的频谱数据（DSPt）。 基于输入包络数据（DEVin）和转换频谱数据（DSPt），数据生成部分指定与转换声音的频谱（SPt）形状对应的频谱（SPnew），并具有基本相同 频谱包络作为输入语音的频谱包络（EVin），并且数据产生部分生成指示频谱（SPnew）的新频谱数据（DSPnew）。 反向FFT部分和输出处理部分基于新的频谱数据（DSPnew）生成输出语音信号（Snew）。

公开(公告)号：US07796748B2

公开(公告)日：2010-09-14

申请号：US10438143

申请日：2003-05-15

Applicant: Pierre Bonnard ,  Ivan Bourmeyster ,  Xavier Fourquin ,  Pierre Ladouce

Inventor： Pierre Bonnard ,  Ivan Bourmeyster ,  Xavier Fourquin ,  Pierre Ladouce

IPC: H04M1/00 ,  H04M9/00

CPC classification number: H04M1/72563 ,  G10L19/00 ,  G10L2021/0135

Abstract: A telecommunication terminal receives an analog speech signal from a user of the terminal and converts the analog speech signal into a digital signal. A vocoder applies source coding to the speech signal and extracts reconstruction parameters from the speech signal. The reconstruction parameters are modified so that the transmitted voice associated with the signal is modified.

Abstract translation: 电信终端从终端的用户接收模拟语音信号，并将模拟语音信号转换为数字信号。 语音编码器对语音信号应用源编码，并从语音信号中提取重构参数。 对重建参数进行修改，使得与信号相关联的传输语音被修改。