公开(公告)号：US20180137875A1

公开(公告)日：2018-05-17

申请号：US15868599

申请日：2018-01-11

Applicant: TENCENT TECHNOLOGY (SHENZHEN) COMPANY LIMITED

Inventor： Yuanyuan LIU ,  Guangjun LIU ,  Guoli LU ,  Fen FU

IPC: G10L21/013 ,  H04L29/08

CPC classification number: G10L21/013 ,  G10L21/003 ,  G10L2021/0135 ,  H04L67/1097

Abstract: Method, apparatus, and storage medium for voice imitation are provided. The voice imitation method, includes: separately obtaining a training voice of a source user and training voices of a plurality of imitation users including a target user; determining, according to the training voice of the source user and a training voice of the target user, a conversion rule for converting the training voice of the source user into the training voice of the target user; collecting voice information of the source user; and converting the voice information of the source user into an imitation voice of the target user according to the conversion rule.

公开(公告)号：US09947341B1

公开(公告)日：2018-04-17

申请号：US15409400

申请日：2017-01-18

Applicant: Interviewing.io, Inc.

Inventor： Andrew Tatanka Marsh ,  Steven Young Yi

IPC: G10L19/14 ,  G10L25/24 ,  G10L21/007 ,  G10L25/18 ,  G10L21/038

CPC classification number: G10L25/24 ,  G10L21/007 ,  G10L25/18 ,  G10L2021/0135

Abstract: A voice signal may be adjusted to mask traits such as the gender of a speaker by separating source and filter components of a voice signal using cepstral analysis, adjusting the components based on pitch and formant parameters, and synthesizing a modified signal. Features are disclosed to support real-time voice masking in a computer network by limiting computational complexity and reducing delays in processing and transmission while maintaining signal quality.

公开(公告)号：US20170249953A1

公开(公告)日：2017-08-31

申请号：US14253853

申请日：2014-04-15

Applicant: SPEECH MORPHING SYSTEMS, INC.

Inventor： Fathy Yassa ,  Benjamin Reaves ,  Steve Pearson

IPC: G10L21/013 ,  G10L25/90 ,  G10L25/51 ,  G10L15/02

CPC classification number: G10L21/013 ,  G10L13/06 ,  G10L15/02 ,  G10L25/51 ,  G10L25/90 ,  G10L2015/022 ,  G10L2015/025 ,  G10L2021/0135

Abstract: Method and apparatus for reducing a size of databases required for recorded speech data.

公开(公告)号：US09728202B2

公开(公告)日：2017-08-08

申请号：US15083276

申请日：2016-03-28

Applicant: VONAGE AMERICA INC.

Inventor： Tzahi Efrati

IPC: G10L21/00 ,  G10L21/003 ,  G10L15/00 ,  G10L21/013

CPC classification number: G10L21/003 ,  G10L15/005 ,  G10L2021/0135 ,  H04M3/51 ,  H04M2203/2061

Abstract: A method for voice modification during a telephone call comprising receiving a source audio signal associated with at least one participant, wherein the source audio signal comprises a voice of the at least one participant, detecting a source dialect of the at least one participant, selecting a target dialect based on at least a characteristic of a target participant and creating a modulated audio signal based on the source audio signal, the source dialect, and the target dialect and transmitting the modulated audio signal to the target participant.

公开(公告)号：US20170208175A1

公开(公告)日：2017-07-20

申请号：US15474667

申请日：2017-03-30

Applicant: United Services Automobile Association (USAA)

Inventor： Vijay Jayapalan ,  Greg Yarbrough ,  Eric Smith

IPC: H04M3/51 ,  G10L13/033 ,  G10L13/04

CPC classification number: H04M3/5166 ,  G10L13/0335 ,  G10L13/043 ,  G10L2021/0135 ,  H04M3/42221 ,  H04M3/4936 ,  H04M3/5183 ,  H04M2201/39 ,  H04M2203/255 ,  H04M2203/306

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for receiving an input from an agent during a call with a caller where the input directs one or more processors to inject a recorded statement in the agent's voice into the call, and where the recorded statement in the agent's voice is stored in a computer-readable file. Obtaining the recorded statement in the agent's voice based on data associated with the input and in response to receiving the input. And causing the recorded statement in the agent's voice to be inserted into a media stream of the call.

公开(公告)号：US20170092286A1

公开(公告)日：2017-03-30

申请号：US15378107

申请日：2016-12-14

Applicant: International Business Machines Corporation

Inventor： Alexander Sorin

IPC: G10L21/013 ,  G10L13/033 ,  G10L25/24 ,  G10L15/08

CPC classification number: G10L21/013 ,  G10L13/0335 ,  G10L15/08 ,  G10L21/003 ,  G10L21/01 ,  G10L25/24 ,  G10L2021/0135

Abstract: A method comprising: receiving an utterance, an original pitch contour of the utterance, and a target pitch contour for the utterance, wherein the utterance comprises a plurality of consecutive frames, and wherein at least one of said frames is a voiced frame; calculating an original intensity contour of said utterance; generating a pitch modified utterance based on the target pitch contour; calculating an intensity modification factor for each of said frames, based on said original pitch contour and on said target pitch contour, to produce a sequence of intensity modification factors corresponding to said plurality of consecutive frames; calculating a final intensity contour for said utterance by applying said intensity modification factors to said original intensity contour; and generating a coherently modified speech signal by time dependent scaling of the intensity of said pitch modified utterance according to said final intensity contour.

公开(公告)号：US09454963B2

公开(公告)日：2016-09-27

申请号：US13799962

申请日：2013-03-13

Applicant: KABUSHIKI KAISHA TOSHIBA

Inventor： Javier Latorre-Martinez ,  Vincent Ping Leung Wan ,  Kean Kheong Chin ,  Mark John Francis Gales ,  Katherine Mary Knill ,  Masami Akamine ,  Byung Ha Chung

IPC: G10L15/00 ,  G10L15/26 ,  G10L13/033 ,  G10L13/08 ,  G10L21/013

CPC classification number: G10L15/26 ,  G10L13/033 ,  G10L13/08 ,  G10L2021/0135

Abstract: A text-to-speech method for simulating a plurality of different voice characteristics includes dividing inputted text into a sequence of acoustic units; selecting voice characteristics for the inputted text; converting the sequence of acoustic units to a sequence of speech vectors using an acoustic model having a plurality of model parameters provided in clusters each having at least one sub-cluster and describing probability distributions which relate an acoustic unit to a speech vector; and outputting the sequence of speech vectors as audio with the selected voice characteristics. A parameter of a predetermined type of each probability distribution is expressed as a weighted sum of parameters of the same type using voice characteristic dependent weighting. In converting the sequence of acoustic units to a sequence of speech vectors, the voice characteristic dependent weights for the selected voice characteristics are retrieved for each cluster such that there is one weight per sub-cluster.

Abstract translation: 用于模拟多个不同语音特征的文本到语音方法包括将输入的文本划分为声学单元序列; 选择输入文本的语音特征; 使用具有多个模型参数的声学模型将所述声学单元的序列转换为语音向量序列，所述多个模型参数在每个具有至少一个子簇的簇中描述，并描述将声学单元与语音向量相关联的概率分布; 并输出所述语音向量序列作为具有所选语音特征的音频。 每个概率分布的预定类型的参数被表示为使用语音特性依赖加权的相同类型的参数的加权和。 在将声音单元的序列转换为语音向量序列时，针对每个群集检索所选语音特征的语音特征依赖权重，使得每个子群集存在一个权重。

公开(公告)号：US09401157B2

公开(公告)日：2016-07-26

申请号：US14279489

申请日：2014-05-16

Applicant: Richard Fink, IV

Inventor： Richard Fink, IV

IPC: G10L25/00 ,  G10L19/06 ,  G10L25/90 ,  G10L21/003 ,  G10L13/033 ,  G09B15/00 ,  G09B19/00 ,  G10L21/013

CPC classification number: G10L21/003 ,  G09B15/00 ,  G09B19/00 ,  G10L13/033 ,  G10L2021/0135

Abstract: The disclosure provides a customizable system for modifying voice dimensions. The system comprises a program interface located on an electronic device. The program interface is used to manipulate user input from one or more individuals relating to voice parameters. Instructions are then created by the program interface that allow for one or more individuals to modify the voice dimensions of the one or more individuals by following the instructions.The disclosure further provides a method for modifying an individual's voice dimensions. The method comprises identifying one or more dimensions in an individual's vocal dimensions that are to be modified. On an electronic device, a voice exercise is created by selecting at least one parameter that modifies the one or more dimensions in an individual's voice. Instructions created by the electronic device that are based on the selection of at least one parameter are then followed by the individual.

Abstract translation: 本公开提供了一种用于修改语音维度的可定制系统。 该系统包括位于电子设备上的程序接口。 程序界面用于操纵一个或多个个人与语音参数有关的用户输入。 然后由程序界面创建允许一个或多个个人通过遵循说明来修改一个或多个个人的语音维度的指令。 本公开还提供了一种用于修改个人的语音维度的方法。 该方法包括识别要修改的个人声部维度中的一个或多个维度。 在电子设备上，通过选择修改个人语音中的一个或多个维度的至少一个参数来创建语音练习。 由电子设备创建的基于至少一个参数的选择的指令随后由该个体追踪。

公开(公告)号：US20160019912A1

公开(公告)日：2016-01-21

申请号：US14332729

申请日：2014-07-16

Applicant: International Business Machines Corporation

Inventor： Franck Barillaud ,  Insoo Cho ,  Dan Christiani ,  Mark R. Thill ,  David S. Zhang

IPC: G10L25/48 ,  G10L25/27 ,  G10L15/02

CPC classification number: G10L25/48 ,  G10L15/02 ,  G10L21/007 ,  G10L25/27 ,  G10L2021/0135

Abstract: Modulating a voice signal is provided. The voice signal corresponding to a voice communication is received from a sending voice communication device via a network. Voice signal features corresponding to the voice communication are extracted. A set of voice signal filters are selected to modulate the extracted voice signal features corresponding to the voice communication to an average voice signal associated with a geographic area where the voice communication is destined for. The voice signal features corresponding to the voice communication are modulated by applying the selected set of voice signal filters to generate the average voice signal associated with the geographic area where the voice communication is destined for.

Abstract translation: 提供调制语音信号。 通过网络从发送语音通信设备接收对应于语音通信的语音信号。 提取与语音通信对应的语音信号。 选择一组语音信号滤波器以将与语音通信相对应的提取的语音信号特征调制为与语音通信所针对的地理区域相关联的平均语音信号。 通过应用所选择的一组语音信号滤波器来调制对应于语音通信的语音信号，以产生与语音通信所针对的地理区域相关联的平均语音信号。

公开(公告)号：US20160005403A1

公开(公告)日：2016-01-07

申请号：US14631464

申请日：2015-02-25

Applicant: Google Inc.

Inventor： Ioannis Agiomyrgiannakis ,  Zoi Roupakia

IPC: G10L17/00

CPC classification number: G10L15/07 ,  G10L17/06 ,  G10L25/75 ,  G10L2021/0135

Abstract: A device may receive data indicative of a plurality of speech sounds associated with first voice characteristics of a first voice. The device may receive an input indicative of speech associated with second voice characteristics of a second voice. The device may map at least one portion of the speech of the second voice to one or more speech sounds of the plurality of speech sounds of the first voice. The device may compare the first voice characteristics with the second voice characteristics based on the map. The comparison may include vocal tract characteristics, nasal cavity characteristics, and voicing characteristics. The device may determine a given representation configured to associate the first voice characteristics with the second voice characteristics. The device may provide an output indicative of pronunciations of the one or more speech sounds of the first voice according to the second voice characteristics based on the given representation.

Abstract translation: 设备可以接收指示与第一语音的第一语音特征相关联的多个语音的数据。 设备可以接收指示与第二语音的第二语音特征相关联的语音的输入。 设备可以将第二语音的语音的至少一部分映射到第一语音的多个语音的一个或多个语音。 设备可以基于地图将第一语音特征与第二语音特征进行比较。 比较可以包括声道特征，鼻腔特征和发音特征。 设备可以确定被配置为将第一语音特征与第二语音特征相关联的给定表示。 该装置可以基于给定的表示，根据第二语音特征提供指示第一语音的一个或多个语音的发音的输出。