公开(公告)号：US20060268757A1

公开(公告)日：2006-11-30

申请号：US11438834

申请日：2006-05-23

Applicant: Fumihiro Horikawa

Inventor： Fumihiro Horikawa

IPC: H04B7/185

CPC classification number: H04M1/6008 ,  G10L2021/0135 ,  H04M1/663 ,  H04M1/72563

Abstract: A telephone includes: a voice changer for converting the original voice of the user; an acquisition unit for acquiring information of the call-origin telephone at the time of an incoming call; a memory in which conditions for using the voice changer have been registered in advance; a determination unit for determining whether to use the voice changer based on information of the call-origin telephone that has been acquired by the acquisition unit and conditions that have been registered in the memory, and based on the result of determination, controlling the voice changer; and a switch unit for switching the state of use of the voice changer during a conversation.

Abstract translation: 电话包括：用于转换用户原始语音的语音转换器; 获取单元，用于在来电时获取呼叫来电电话的信息; 预先注册了使用语音更换器的条件的存储器; 确定单元，用于基于由获取单元获取的呼叫起始电话的信息和已经登记在存储器中的条件来确定是否使用语音更换器，并且基于确定结果，控制语音更换器 ; 以及用于在会话期间切换语音更换器的使用状态的开关单元。

公开(公告)号：US20060173676A1

公开(公告)日：2006-08-03

申请号：US11345023

申请日：2006-01-31

Applicant: Hideki Kemmochi ,  Jordi Bonada

Inventor： Hideki Kemmochi ,  Jordi Bonada

IPC: G10L11/04

CPC classification number: G10L13/06 ,  G10L25/18 ,  G10L2021/0135

Abstract: In a voice synthesizer, an envelope acquisition portion obtains a spectral envelope of a reference frequency spectrum of a given voice. A spectrum acquisition portion obtains a collective frequency spectrum of a plurality of voices which are generated in parallel to one another. An envelope adjustment portion adjusts a spectral envelope of the collective frequency spectrum obtained by the spectrum acquisition portion so as to approximately match with the spectral envelope of the reference frequency spectrum obtained by the envelope acquisition portion. A voice generation portion generates an output voice signal from the collective frequency spectrum having the spectral envelope adjusted by the envelope adjustment portion.

公开(公告)号：US20060095265A1

公开(公告)日：2006-05-04

申请号：US10977178

申请日：2004-10-29

Applicant: Min Chu ,  Yong Zhao ,  Sheng Zhao

Inventor： Min Chu ,  Yong Zhao ,  Sheng Zhao

IPC: G10L13/06

CPC classification number: G10L13/033 ,  G10L2021/0135

Abstract: A method for synthesizing speech from text includes receiving one or more waveforms characteristic of a voice of a person selected by a user, generating a personalized voice font based on the one or more waveforms, and delivering the personalized voice font to the user's computer, whereby speech can be synthesized from text, the speech being in the voice of the selected person, the speech being synthesized using the personalized voice font. A system includes a text-to-speech (TTS) application operable to generate a voice font based on speech waveforms transmitted from a client computer remotely accessing the TTS application.

Abstract translation: 一种用于从文本合成语音的方法包括接收用户选择的人物的声音特征的一个或多个波形，基于一个或多个波形产生个性化语音字体，并将个性化语音字体传送到用户的计算机，由此 可以从文本合成语音，语音在所选择的人的语音中，使用个性化语音字体合成语音。 一种系统包括文本到语音（TTS）应用，其可操作以基于远程访问TTS应用的客户端计算机发送的语音波形来生成语音字体。

公开(公告)号：US07003462B2

公开(公告)日：2006-02-21

申请号：US10955880

申请日：2004-09-30

Applicant: Craig R. Shambaugh ,  Anthony Dezonno ,  Mark J. Power ,  Kenneth Venner ,  Jared Bluestein ,  Jim F. Martin ,  Darryl Hymel ,  Laird C. Williams

Inventor： Craig R. Shambaugh ,  Anthony Dezonno ,  Mark J. Power ,  Kenneth Venner ,  Jared Bluestein ,  Jim F. Martin ,  Darryl Hymel ,  Laird C. Williams

IPC: G10L21/00

CPC classification number: G10L13/033 ,  G10L21/00 ,  G10L2021/0135 ,  H04M3/51 ,  H04M2201/40

Abstract: A method and apparatus are provided for adjusting a content of an oral presentation provided by an agent of an organization and perceived by a human target of the organization based upon an objective of the organization. The method includes the steps of detecting a content of the oral presentation provided by the agent and modifying the oral presentation provided by the agent to produce the oral presentation perceived by the human target based upon the detected content and the organizational objective.

Abstract translation: 提供了一种方法和装置，用于基于组织的目标来调整由组织的代理提供并且由组织的人类目标所感知的口头呈现的内容。 该方法包括以下步骤：基于检测到的内容和组织目标，检测由代理提供的口头呈现的内容并修改由代理提供的口头表达以产生由人类目标感知的口头呈现。

公开(公告)号：US20040230421A1

公开(公告)日：2004-11-18

申请号：US10438642

申请日：2003-05-15

Inventor： Juergen Cezanne ,  Sunil K. Gupta ,  Chetan Vinchhi

IPC: G10L011/04

CPC classification number: G10L21/003 ,  G10L21/00 ,  G10L2021/0135

Abstract: The intonation of speech is modified by an appropriate combination of resampling and time-domain harmonic scaling. Resampling increases (upsampling) or decreases (downsampling) the number of data points in a signal. Harmonic scaling adds or removes pitch cycles to or from a signal. The pitch of a speech signal can be increased by combining downsampling with harmonic scaling that adds an appropriate number of pitch cycles. Alternatively, pitch can be decreased by combining upsampling with harmonic scaling that removes an appropriate number of pitch cycles. The present invention can be implemented in an automated speech-therapy tool that is able to modify the intonation of prerecorded reference speech signals for playback to a user to emphasize the correct pronunciation by increasing the pitch of selected portions of words or phrases that the user had previously mispronounced.

Abstract translation: 通过重采样和时域谐波缩放的适当组合来修改语音的语调。 重采样增加（上采样）或降低（下采样）信号中数据点的数量。 谐波缩放可以增加或去除信号的音调周期。 语音信号的音调可以通过将下采样与谐波缩放相结合来增加，该谐波缩放增加适当数量的音调周期。 或者，可以通过组合上采样与谐波缩放来去除适当数量的音调周期来减小音调。 本发明可以在自动言语治疗工具中实现，该自动语音治疗工具能够通过增加用户所拥有的单词或短语的选定部分的音调来修改预先记录的参考语音信号的音调以便播放给用户以强调正确的发音 以前是错误的。

公开(公告)号：US20030100345A1

公开(公告)日：2003-05-29

申请号：US09996524

申请日：2001-11-28

Inventor： Arnold J. Gum

IPC: H04M001/00

CPC classification number: H04M1/6016 ,  G10L21/00 ,  G10L21/0364 ,  G10L2021/0135 ,  H04M1/72519

Abstract: An apparatus for providing a custom profile in a wireless device, and a method of modifying an audio profile in a wireless device, are disclosed. The apparatus includes a memory into which at least one criterion is entered by the user, a receiver that receives an audio signal, a comparator that receives the audio signal from the receiver, and that receives at least a first of the least one criterion from the memory, and that compares the audio signal to the first criterion, and an adjustor that adjusts the audio signal based on the result from the comparator. The method includes the steps of entering, by a user of the wireless device, of a first criterion, comparing an audio signal received by the wireless device to the first criterion, adjusting the audio signal based on the output of the comparing step, and playing the adjusted audio signal to the user, or broadcasting the adjusted audio signal to a remote caller.

Abstract translation: 公开了一种用于在无线设备中提供定制简档的设备，以及修改无线设备中的音频简档的方法。 该装置包括存储器，用户至少输入一个标准，接收音频信号的接收器，从接收器接收音频信号的比较器，以及接收来自接收机的至少一个标准中的至少一个标准的存储器 存储器，并且将音频信号与第一标准进行比较;以及调整器，其基于比较器的结果来调整音频信号。 该方法包括以下步骤：由无线设备的用户输入第一标准，将由无线设备接收的音频信号与第一标准进行比较，基于比较步骤的输出调整音频信号，并播放 调整后的音频信号给用户，或者将经调整的音频信号广播给远程呼叫者。

公开(公告)号：US20020120450A1

公开(公告)日：2002-08-29

申请号：US09792928

申请日：2001-02-26

Inventor： Jean-Claude Junqua ,  Florent Perronnin ,  Roland Kuhn ,  Patrick Nguyen

IPC: G10L013/00

CPC classification number: G10L13/04 ,  G10L2021/0135

Abstract: The speech synthesizer is personalized to sound like or mimic the speech characteristics of an individual speaker. The individual speaker provides a quantity of enrollment data, which can be extracted from a short quantity of speech, and the system modifies the base synthesis parameters to more closely resemble those of the new speaker. More specifically, the synthesis parameters may be decomposed into speaker dependent parameters, such as context-independent parameters, and speaker independent parameters, such as context dependent parameters. The speaker dependent parameters are adapted using enrollment data from the new speaker. After adaptation, the speaker dependent parameters are combined with the speaker independent parameters to provide a set of personalized synthesis parameters. To adapt the parameters with a small amount of enrollment data, an eigenspace is constructed and used to constrain the position of the new speaker so that context independent parameters not provided by the new speaker may be estimated.

Abstract translation: 语音合成器被个性化以发音或模仿单个扬声器的语音特征。 单个扬声器提供一定数量的登记数据，其可以从短语言中提取，并且系统将基本合成参数修改为更接近于新说话者的参考数据。 更具体地，合成参数可以被分解为与扬声器相关的参数，诸如与上下文无关的参数，以及与扬声器无关的参数，诸如与上下文相关的参数。 使用来自新扬声器的注册数据来调整与扬声器相关的参数。 在适应之后，将扬声器依赖参数与扬声器独立参数组合以提供一组个性化合成参数。 为了使参数具有少量的注册数据，构造本征空间并用于约束新的说话者的位置，以便可以估计不能由新发言者提供的上下文独立参数。

公开(公告)号：US20020111796A1

公开(公告)日：2002-08-15

申请号：US09796814

申请日：2001-02-28

Inventor： Yasushi Nemoto

IPC: G10L019/14

CPC classification number: H04M1/6016 ,  G10L21/0364 ,  G10L2021/0135

Abstract: There is provided a voice processing technology and device utilizing the voice processing technology, capable of making the voice on the telephone receiver easy to hear according to the frequency. This invention utilizes a frequency conversion means capable of converting the input voice frequency to a desired frequency. The frequency conversion level or frequency shift can be optionally set for each frequency. The frequency is not changed if the input voice frequency is low. The higher the voice frequency, the greater the frequency conversion shift to a low frequency range for an easy to hear voice.

Abstract translation: 提供了一种利用语音处理技术的语音处理技术和设备，能够根据频率使得电话接收机上的语音容易听到。 本发明利用能够将输入语音频率转换成期望频率的频率转换装置。 可以为每个频率选择设置频率转换电平或频移。 如果输入语音频率低，则频率不变。 语音频率越高，频率越高，转换到低频范围就越容易听到声音。

公开(公告)号：US20010033652A1

公开(公告)日：2001-10-25

申请号：US09778675

申请日：2001-02-07

Applicant: Speech Technology and Applied Research Corporation

Inventor： Joel M. MacAuslan ,  Venkatesh Chari ,  Richard Goldhor ,  Carol Espy-Wilson

IPC: H04M009/08

CPC classification number: G10L25/93 ,  G10L2021/0135 ,  G10L2025/783 ,  G10L2025/937

Abstract: A technique for separating an acoustic signal into a voiced (V) component corresponding to an electrolaryngeal source and an unvoiced (U) component corresponding to a turbulence source. The technique can be used to improve the quality of electrolaryngeal speech, and may be adapted for use in a special purpose telephone. A method according to the invention extracts a segment of consecutive values from the original stream of numerical values, and performs a discrete Fourier transform on the this first group of values. Next, a second group of values is extracted from components of the discrete Fourier transform result which correspond to an electrolaryngeal fixed repetition rate, F0, and harmonics thereof. An inverse-Fourier transform is applied to the second group of values, to produce a representation of a segment of the V component. Multiple V component segments are then concatenated to form a V component sample stream. Finally, the U component is determined by subtracting the V component sample stream from the original stream of numerical values.

Abstract translation: 一种用于将声信号分离成对应于电流源和与湍流源相对应的无声（U）分量的有声（V）分量的技术。 该技术可用于提高电咽喉语言的质量，并可适用于专用电话机。 根据本发明的方法从原始数值流中提取一段连续值，并对该第一组值执行离散傅立叶变换。 接下来，从对应于电咽固定重复率F0及其谐波的离散付里叶变换结果的分量中提取第二组值。 将傅里叶逆变换应用于第二组值，以产生V分量的分段的表示。 然后将多个V分量段连接以形成V分量样本流。 最后，通过从原始数据流中减去V分量样本流来确定U分量。

公开(公告)号：US6115684A

公开(公告)日：2000-09-05

申请号：US902546

申请日：1997-07-29

Applicant: Hideki Kawahara ,  Ikuyo Masuda

Inventor： Hideki Kawahara ,  Ikuyo Masuda

IPC: G10L11/00 ,  G10L21/00 ,  G10L21/04 ,  G10L101/02

CPC classification number: G10L25/48 ,  G10L21/04 ,  G10L2021/0135

Abstract: At a smoothing spectrogram calculation portion, a triangular interpolation function having a frequency width twice that of the fundamental frequency of a signal is obtained based on information on the fundamental frequency of the signal. The interpolation function and a spectrum obtained at an adaptive frequency analysis portion are convoluted in the direction of frequency. Then, using a triangular interpolation function having a time length twice that of a fundamental period, the spectrum interpolated in the frequency direction described above is further interpolated in the temporal direction, in order to produce a smoothed spectrogram having the space between grid points on the time-frequency plane filled with the surface of a bilinear function. Using the smoothed spectrogram, a speech sound is transformed. Therefore, the influence of periodicity in the frequency direction and the temporal direction can be reduced.

Abstract translation: 在平滑频谱图计算部分，基于信号的基频的信息，获得频率宽度为信号的基频两倍的三角插值函数。 在自适应频率分析部分获得的内插函数和频谱在频率方向上被卷积。 然后，使用具有基本周期的时间长度的两倍的时间长度的三角插值函数，在时间方向上进一步内插在上述频率方向上插入的频谱，以便产生平滑的谱图，该平滑的谱图具有在 充满双线性函数表面的时频平面。 使用平滑的频谱图，转换语音。 因此，可以减少周期性在频率方向和时间方向上的影响。