公开(公告)号：EP0792502A1

公开(公告)日：1997-09-03

申请号：EP96923669.0

申请日：1996-06-28

Applicant: MOTOROLA, INC.

Inventor： DAVIS, Walter, Lee ,  HUANG, Jian-Cheng ,  JASINSKI, Leon

IPC: G10L19 ,  H03M7 ,  H04B14 ,  H04Q7

CPC classification number: G10L19/0212 ,  G10L25/27

Abstract: An apparatus and method for processing a voice message to provide low bit rate speech transmission processes the voice message to generate speech parameters which are arranged into a two dimensional parameter matrix (502) including a sequence of parameter frames. The two dimensional parameter matrix (502) is transformed using a predetermined two dimensional matrix transformation function (414) to obtain a two dimensional transform matrix (506). Distance values representing distances between templates of a set of predetermined templates and the two dimensional transform matrix (506) are then derived. The distance values derived are identified by indexes identifying the templates of the set of predetermined templates. The distance values derived are compared, and an index corresponding to a template of the set of predetermined templates having a shortest distance is selected and then transmitted.

公开(公告)号：WO2004097618A3

公开(公告)日：2004-11-11

申请号：PCT/EP2004/050597

申请日：2004-04-23

Applicant: MOTOROLA INC ,  MOTOROLA LIMITED ,  ZHEN, Li-Xin ,  HUANG, Jian-Cheng ,  LUO, Xi Ping

Inventor： ZHEN, Li-Xin ,  HUANG, Jian-Cheng ,  LUO, Xi Ping

IPC: G06F3/033

Abstract: A method for allowing two screen functions to share a common display are (35) of an interactive display screen (5) associated with an electronic device (1). The method includes determining automatically (21) a required function to be performed in the common display are (35). The required function typically being a character scribing function (25) and a candidate character display function (24) associated with a scribed character scribed on the common display are (35). The method performs controlling the common display are (35) in order to perform only the required function.

公开(公告)号：WO1997027578A1

公开(公告)日：1997-07-31

申请号：PCT/US1997000329

申请日：1997-01-07

Applicant: MOTOROLA INC.

Inventor： MOTOROLA INC. ,  HUANG, Jian-Cheng ,  SIMPSON, Floyd ,  LI, Xiaojun

IPC: G10L03/02

CPC classification number: G10L25/90 ,  G10L19/09 ,  G10L19/12 ,  G10L21/013

Abstract: A speech analyzer (107) compresses a voice message for transmission and includes an LPC analyzer (406) which derives spectral vectors from segments of speech; a memory (1910) which stores predetermined spectral vectors identified by indexes, the indexes also identifying predetermined voicing vectors stored within a receiver; a quantizer (422) which compares the spectral vector derived with the predetermined spectral vectors to select one of the predetermined spectral vectors; and an output buffer for storing the index identifying the predetermined spectral vector selected. The speech analyzer (107) also includes a pitch determiner (414) which includes a pitch function generator (414) which generates a pitch function from a segment of speech. A pitch enhancer (1116) enhances the pitch function of a current segment of speech utilizing the pitch function of one or more sequential segments of speech and a pitch detector (1118) detects the pitch of the current segment of speech.

Abstract translation: 语音分析器（107）压缩用于发送的语音消息，并且包括从语音段导出频谱向量的LPC分析器（406） 存储器（1910），其存储由索引识别的预定频谱矢量，所述索引还识别存储在接收机内的预定语音向量; 量化器（422），其将导出的频谱矢量与预定频谱矢量进行比较，以选择预定频谱矢量之一; 以及用于存储识别所选择的预定频谱矢量的索引的输出缓冲器。 语音分析器（107）还包括音调确定器（414），音调确定器（414）包括音调函数发生器（414），该音调函数发生器从语音段生成音调函数。 音调增强器（1116）利用一个或多个连续语音段的音调函数来增强当前语音段的音调函数，并且音调检测器（1118）检测当前语音段的间距。

公开(公告)号：WO2007030233A2

公开(公告)日：2007-03-15

申请号：PCT/US2006/029912

申请日：2006-08-01

Applicant: MOTOROLA INC. ,  CAO, Zhen-Hai ,  HUANG, Jian-Cheng ,  ZU, Yi-Qing

Inventor： CAO, Zhen-Hai ,  HUANG, Jian-Cheng ,  ZU, Yi-Qing

IPC: G10L15/18

CPC classification number: G10L15/22 ,  G10L13/04

Abstract: An electronic device (200) for speech dialog includes functions that receive (205, 105) an utterance that includes an instantiated variable (215), perform voice recognition (210, 115, 120) of the instantiated variable to determine a most likely set of acoustic states (220) and a corresponding sequence of phonemes with stress information (215), determine prosodic characteristics (272, 274, 276, 130) for a synthesized value of the instantiated variable (236) from the sequence of phonemes with stress information and a set of stored prosody models. The electronic device generates (335, 140) a synthesized value of the instantiated variable using the most likely set of acoustic states and the prosodic characteristics of the instantiated variable.

Abstract translation: 用于语音对话的电子设备（200）包括接收（205,105）包括实例化的变量（215）的话语的函数，执行实例化的语音​​识别（210,115,120） 以确定最可能的声学状态集合（220）和具有应力信息（215）的相应音素序列，从实例化变量（236）的合成值确定韵律特征（272,274,276,130） 具有压力信息的音素序列和一组存储的韵律模型。 电子设备使用最可能的声学状态集合和实例化变量的韵律特征来生成（335,140）实例化变量的合成值。

公开(公告)号：WO2004111921A1

公开(公告)日：2004-12-23

申请号：PCT/EP2004/051003

申请日：2004-06-02

Applicant: MOTOROLA INC ,  MOTOROLA LIMITED ,  HUANG, Jian-Cheng ,  ZHEN, Li-Xin ,  GUO, Feng Jun

Inventor： HUANG, Jian-Cheng ,  ZHEN, Li-Xin ,  GUO, Feng Jun

IPC: G06K9/72

CPC classification number: G06K9/6292 ,  G06K9/222

Abstract: When scribing characters into an electronic device (1) for displaying at a current character position (24), a character recognition package seeks to recognize the scribed character (22) and produces a first list (50) of candidate characters. The candidate characters in the10 first list (50) is put into an initial order based on the degree of similarity between the scribed character and the candidate characters. Additionally a lexicon of possible character pairs is consulted to determine a second list (52) of candidate characters, based on the immediately preceding character to the current character position. The two lists are compared and the first list is displayed in a display order which may or may not differ from the initial order, depending on the degree of overlap between the two lists. The invention is particularly useful when scribing complex characters such as Chinese characters, and/or when used in devices with a limited memory, for example pocket devices, such as mobile telephones, personal digital assistants (PDAs), global positioning system (GPS) navigators, or the like.

Abstract translation: 当将字符划分成用于在当前字符位置（24）显示的电子设备（1）时，字符识别包试图识别划刻字符（22）并产生候选字符的第一列表（50）。 基于被划刻的字符与候选字符之间的相似程度，将第10列表（50）中的候选字符置入初始顺序。 此外，参考可能的字符对的词典以基于当前字符位置的紧接在前的字符来确定候选字符的第二列表（52）。 比较两个列表，并且根据两个列表之间的重叠程度，以与初始顺序不同的显示顺序显示第一列表。 本发明在诸如汉字等复杂字符的划线时和/或当用于具有有限存储器的设备中时，特别有用，例如袖珍设备，例如移动电话，个人数字助理（PDA），全球定位系统（GPS）导航器 ，等等。

公开(公告)号：WO1997010585A1

公开(公告)日：1997-03-20

申请号：PCT/US1996011341

申请日：1996-07-08

Applicant: MOTOROLA INC.

Inventor： MOTOROLA INC. ,  HUANG, Jian-Cheng ,  SIMPSON, Floyd ,  LI, Xiaojun

IPC: G10L03/02

CPC classification number: G10L19/06 ,  G10L2019/0013

Abstract: A method and apparatus are provided for a low bit rate speech transmission. Speech spectral parameter vectors are generated from a voice message and stored in a sequence of speech spectral parameter vectors within a speech spectral parameter matrix (602). A first index identifying a first speech parameter template (614) corresponding to a first speech spectral parameter vector (604) of the sequence of speech spectral parameter vectors is transmitted. A subsequent speech spectral parameter vector (608) of the sequence is selected and a subsequent speech parameter template (618) is determined having a subsequent index. One or more intervening interpolated speech parameter templates (620) are interpolated between the first speech parameter template (614) and the subsequent speech parameter template (618). The one or more intervening speech spectral parameter vectors (606) are compared to the corresponding one or more intervening interpolated speech parameter templates (620) to derive a distance. The subsequent index is transmitted when the distance derived is less than or equal to a predetermined distance.

Abstract translation: 提供了一种用于低比特率语音传输的方法和装置。 语音频谱参数矢量从语音消息产生并存储在语音频谱参数矩阵（602）内的语音频谱参数矢量序列中。 发送识别对应于语音频谱参数向量序列的第一语音频谱参数向量（604）的第一语音参数模板（614）的第一索引。 选择该序列的后续语音频谱参数矢量（608），并且确定具有后续索引的后续语音参数模板（618）。 在第一语音参数模板（614）和随后的语音参数模板（618）之间插入一个或多个插入的内插语音参数模板（620）。 将一个或多个中间语音频谱参数矢量（606）与相应的一个或多个插入的内插语音参数模板（620）进行比较以导出距离。 当所导出的距离小于或等于预定距离时，传送随后的索引。

公开(公告)号：WO2007076278A2

公开(公告)日：2007-07-05

申请号：PCT/US2006/062029

申请日：2006-12-13

Applicant: MOTOROLA INC. ,  CHEN, Gui-Lin ,  HUANG, Jian-Cheng ,  YANG, Duan-Duan

Inventor： CHEN, Gui-Lin ,  HUANG, Jian-Cheng ,  YANG, Duan-Duan

IPC: G09G3/24

CPC classification number: G06T13/205 ,  G06T13/40 ,  G10L2021/105

Abstract: A method for animating an image is useful for animating avatars using real-time speech data. According to one aspect, the method includes identifying an upper facial part and a lower facial part of the image (step 705); animating the lower facial part based on speech data that are classified according to a reduced vowel set (step 710); tilting both the upper facial part and the lower facial part using a coordinate transformation model (step 715); and rotating both the upper facial part and the lower facial part using an image warping model (step 720).

Abstract translation: 用于使图像动画化的方法对于使用实时语音数据来动画化头像是有用的。 根据一个方面，该方法包括识别图像的上脸部和下脸部（步骤705）。 基于根据减少的元音组分类的语音数据来对下面部部分进行动画化（步骤710）; 使用坐标变换模型倾斜上脸部和下面部部分（步骤715）; 并使用图像扭曲模型旋转上脸部和下面部部分（步骤720）。

公开(公告)号：WO1997009791A1

公开(公告)日：1997-03-13

申请号：PCT/US1996011694

申请日：1996-07-15

Applicant: MOTOROLA INC.

Inventor： MOTOROLA INC. ,  HUANG, Jian-Cheng ,  XIAOJUN, Li ,  FLOYD, Simpson

IPC: H03M13/00

CPC classification number: G10L19/07 ,  G10L19/005

Abstract: Error detection and correction of a received message, such as a digitized voice message is achieved by generating (318) interpolated vectors for each error vector corresponding to a codebook index in a sequence of codebook indexes representing parameters of portions of the message. A plurality of error corrected candidate vectors for the vector corresponding to the codebook index in error, are generated (322, 324, 326) by flipping one bit in a sequence of bits representing the codebook index in error. The error corrected candidate vector which has a minimal difference from its corresponding interpolated vector is used (338) to replace the error vector. In the case of digital voice, the vectors are spectral vectors which represent spectral information for a time sample of a voice message. An ordering property of vector components is exploited to detect errors in a received codebook index without parity bits.

Abstract translation: 通过对表示信息部分参数的代码簿索引序列中的码本索引生成每个误差向量的内插向量来实现对诸如数字化语音消息的接收消息的错误检测和校正。 通过在表示码本索引的位的序列中翻转一位来产生对应于错误的码本索引的矢量的多个纠错候选向量（322,324,326）。 使用与其对应的内插向量具有最小差异的误差校正候选向量（338）来替换误差向量。 在数字语音的情况下，向量是表示语音消息的时间采样的频谱信息的频谱矢量。 利用矢量分量的排序属性来检测接收到的码本索引中没有奇偶校验位的错误。

公开(公告)号：WO2005034083A1

公开(公告)日：2005-04-14

申请号：PCT/US2004/030468

申请日：2004-09-17

Applicant: MOTOROLA, INC. ,  CHEN, Gui-Lin ,  HUANG, Jian-Cheng

Inventor： CHEN, Gui-Lin ,  HUANG, Jian-Cheng

IPC: G10L13/08

CPC classification number: G10L13/08

Abstract: There is described a method (200) for text to speech synthesis, the method (200) includes receiving (220) a text string and selecting at least one word from the string. Then a step of segmenting (240) the word into a sub-words forming a sub-word sequence with at least one of the sub-words comprising at least two letters. The step of identifying (250) provides for identifying phonemes for the sub-words and step (260) effects concatenating the phonemes into a phoneme sequence. A performing speech synthesis (280) on the phoneme sequence is then conducted.

Abstract translation: 描述了用于文本到语音合成的方法（200），方法（200）包括接收（220）文本串并从字符串中选择至少一个单词。 然后，将该单词分割（240）成为形成子词序列的子词，其中至少一个子词包括至少两个字母。 识别（250）的步骤提供用于识别子词的音素并且步骤（260）将音素连接成音素序列。 然后对音素序列执行语音合成（280）。

公开(公告)号：WO2004097613A2

公开(公告)日：2004-11-11

申请号：PCT/EP2004/050598

申请日：2004-04-23

Applicant: MOTOROLA INC ,  MOTOROLA LIMITED ,  ZHEN, Li-Xin ,  HUANG, Jian-Cheng ,  LYUSTIN, Victoria ,  LI, Jonathan

Inventor： ZHEN, Li-Xin ,  HUANG, Jian-Cheng ,  LYUSTIN, Victoria ,  LI, Jonathan

IPC: G06F3/00

CPC classification number: G06F3/0236

Abstract: A method (20) for guiding a user of an electronic device (1) to select keys on a keyboard (31) of a touch screen (5) on the device, the method includes receiving (22) a reference alphanumeric character, input at the keyboard (32), the reference alphanumeric character identifying a first part of a syllable. The method then performs a searching (23) a database of valid syllables or words to identify valid alphanumeric characters that can immediately follow the reference alphanumeric character. Thereafter, the method performs a step of emphasizing keys (24) on the keyboard (32) that represent the valid alphanumeric characters thereby guiding the user to select one of the keys representing one of said valid alphanumeric characters.

Abstract translation: 一种用于引导电子设备（1）的用户选择所述设备上的触摸屏（5）的键盘（31）上的键的方法（20），所述方法包括：接收（22）参考字母数字字符， 所述键盘（32），所述参考字母数字字符标识音节的第一部分。 该方法然后执行搜索（23）有效音节或单词的数据库，以识别可以立即遵循参考字母数字字符的有效字母数字字符。 此后，该方法执行强调表示有效字母数字字符的键盘（32）上的键（24）的步骤，从而引导用户选择表示所述有效字母数字字符之一的键之一。