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

AU2002243790B2 Method and system for testing speech intelligibility in children 未知
公开(公告)号：AU2002243790B2
公开(公告)日：2005-12-08
申请号：AU2002243790
申请日：2002-02-04
申请人： WISCONSIN ALUMNI RES FOUND
发明人： LITOVSKY RUTH Y
IPC分类号： A61B5/12 , G10L13/04 , G09B007/08 , G10L021/00 , A61B005/00
摘要： A method and system for testing the speech intelligibility of a child comprises providing a set of target sounds as words in the presence and absence of competing sound(s) of a variety of types so as to enable an analysis of the aspects of competing sounds and their respective effects on the speech intelligibility of a child. Locations at which competing sound(s) is provided is varied to enable an evaluation of its effect on the spatial release from masking. The target words used in the test are first determined to be within the vocabulary of the child. The child is required to respond to the target word by selecting a picture representation of the target word from among several picture choices, thus providing an interactive aspect to the test. There may optionally be provided a positive or a negative reinforcement. The sound level at which the target words are presented may vary adaptively according to the child's responses, the change in sound level being determined by a set of rules. The test is repeated over several target words and under a variety of types and locations of competing sounds and the child's responses recorded in a results database. The results are available for further analysis by a user to produce customized output. A computerized system is disclosed that enables the provisioning of the test in a controlled manner, analysis of the data and further engagement the child.

2. 发明申请

US20040243416A1 Speech recognition 审中-公开
标题翻译：语音识别
公开(公告)号：US20040243416A1
公开(公告)日：2004-12-02
申请号：US10453447
申请日：2003-06-02
发明人： Thomas R. Gardos
IPC分类号： G10L021/00
CPC分类号： G10L15/25 , G10L21/06
摘要： An apparatus that includes an image capture device and a support. The image capture device captures images of a user's lips, and the support holds the image capture device in a position substantially constant relative to the user's lips as the user's head moves.
摘要翻译：一种包括图像捕获装置和支架的装置。图像捕获设备捕获用户嘴唇的图像，并且支撑件将图像捕获设备保持在用户头部移动时相对于使用者的嘴唇基本上恒定的位置。

3. 发明申请

US20040243415A1 Architecture for a speech input method editor for handheld portable devices 审中-公开
标题翻译：用于手持便携式设备的语音输入法编辑器的架构
公开(公告)号：US20040243415A1
公开(公告)日：2004-12-02
申请号：US10452429
申请日：2003-06-02
申请人： International Business Machines Corporation
发明人： Patrick M. Commarford , Mario E. De Armas , Burn L. Lewis , James R. Lewis
IPC分类号： G10L021/00
CPC分类号： G06F3/167 , G10L15/26
摘要： A speech input method editor can include a speech toolbar (102) having at least a microphone state/toggle button (104). The speech input method editor can also include a selectable dictation window area (108) used as a temporary dictation target until dictation text is transferred to a target application and a selectable correction window area (112) having at least one among an alternate list (120) for correcting dictated words, an alphabet (114), a spacebar (116), a spell mode reminder (118), or a virtual keyboard (122). The speech input method editor can remain active while using the selectable correction window and while transferring dictation text to the target application. The speech input method editor can further include an alternate input method editor window (112b) used to allow non-speech editing into at least one among the dictation window or to the target application while using the speech input method editor.
摘要翻译：语音输入法编辑器可以包括具有至少麦克风状态/切换按钮（104）的语音工具栏（102）。语音输入方法编辑器还可以包括用作临时听写目标的可选听写窗口区域（108），直到听写文本被传送到目标应用程序，并且可选修正窗口区域（112）具有备选列表（120 ），用于校正指定词，字母表（114），空格键（116），拼写模式提醒（118）或虚拟键盘（122）。语音输入法编辑器可以在使用可选择的校正窗口和将录音文本传送到目标应用程序时保持有效。语音输入法编辑器还可以包括用于在使用语音输入方法编辑器时允许在听写窗口或目标应用程序中的至少一个语音编辑的替代输入法编辑器窗口（112b）。

4. 发明申请

US20040228456A1 Voice activated, voice responsive product locator system, including product location method utilizing product bar code and aisle-situated, aisle-identifying bar code 有权
标题翻译：语音激活，语音响应产品定位系统，包括产品定位方法，使用产品条形码和通道位置，通道识别条形码
公开(公告)号：US20040228456A1
公开(公告)日：2004-11-18
申请号：US10696660
申请日：2003-10-29
申请人： iVoice, Inc.
发明人： Kenneth P. Glynn , Jerome R. Mahoney
IPC分类号： H04M001/64 , G10L017/00 , G10L021/00
CPC分类号： G06Q10/06 , G06Q10/087 , G10L15/00
摘要： The present invention is an item location system which relies upon voice activation and responsiveness to identify location(s) of item(s) sought by a user. The system includes a continuous speech recognition digital signal processor, a programmable microprocessor interfaced therewith, voice input and user feedback mechanisms, including audio and/or video feedback. Preferred embodiments utilize audio feedback to the user. The system also includes sufficient software and equipment to create item-identification/corresponding location-identification data pairs by utilizing item identifying bar codes on the items and matching them to location identifying bar codes physically situated on the corresponding locations. The continuous speech recognition engine utilizes Hidden Markov Models to create real time continuous speech recognition and feedback.
摘要翻译：本发明是一种依靠语音激活和响应性来识别用户所寻求的物品的位置的物品定位系统。该系统包括连续语音识别数字信号处理器，与其接口的可编程微处理器，语音输入和用户反馈机制，包括音频和/或视频反馈。优选实施例使用音频反馈给用户。该系统还包括足够的软件和设备，通过利用项目上识别条形码的项目来标识物品识别/对应的位置识别数据对，并将其与物理位于相应位置上的位置识别条形码进行匹配。连续语音识别引擎利用隐马尔可夫模型创建实时连续语音识别和反馈。

5. 发明申请

US20040220805A1 Method and device for processing time-discrete audio sampled values 有权
标题翻译：用于处理时间离散音频采样值的方法和设备
公开(公告)号：US20040220805A1
公开(公告)日：2004-11-04
申请号：US10479398
申请日：2004-06-25
发明人： Ralf Geiger , Thomas Sporer , Jurgen Koller , Karlheinz Brandenburg , Jurgen Herre
IPC分类号： G10L019/14 , G10L021/00
CPC分类号： G10L19/0212 , G06F17/147
摘要： In order to obtain an integer transform, which provides integer output values, the TDAC function of a MDCT is explicitly carried out in the time domain before the forward transform. In overlapping windows, this results in a Givens rotation which may be represented by lifting matrices, wherein time-discrete sampled values of an audio signal may at first be summed up on a pair-wise basis to build a vector so as to be sequentially provided with a lifting matrix. In accordance with the invention, after each multiplication of a vector by a lifting matrix, a rounding step is carried out such that, on the output-side, only integers will result. By transforming the windowed integer sampled value with an integer transform, a spectral representation with integer spectral values may be obtained. The inverse mapping with an inverse rotation matrix and corresponding inverse lifting matrices results in an exact reconstruction. The inventive concept provides a lossless transform which may be coupled immediately with an entropy-encoder without quantizing so as to obtain a windowing and transform method which may be favorably implemented on a hardware-basis.
摘要翻译：为了获得提供整数输出值的整数变换，MDCT的TDAC功能在正向变换之前的时域中被明确地执行。在重叠窗口中，这导致Givens旋转，其可以由提升矩阵表示，其中音频信号的时间离散采样值可以首先在成对的基础上相加以构建向量以便顺序地提供与提升矩阵。根据本发明，在通过提升矩阵对向量进行每次乘法之后，执行舍入步骤，使得在输出侧仅将导致整数。通过用整数变换变换窗口整数采样值，可以获得具有整数频谱值的频谱表示。具有逆旋转矩阵和对应的反提升矩阵的逆映射导致精确重建。本发明的概念提供了一种无损变换，其可以与熵编码器立即耦合而不进行量化，以获得可以在硬件上有利地实现的加窗和变换方法。

6. 发明申请

US20040199391A1 Portable voice/letter processing apparatus 审中-公开
标题翻译：便携式语音/信件处理设备
公开(公告)号：US20040199391A1
公开(公告)日：2004-10-07
申请号：US10477947
申请日：2004-04-23
发明人： Tae-Soo Yoon , Hoon Choi
IPC分类号： G10L021/00 , G01L013/00 , G10L011/00
CPC分类号： G10L15/26 , A63H2200/00
摘要： A portable voice/letter processing apparatus includes an input unit for receiving input data: a storing unit for storing compressed data: a control unit for generating a control signal so that the compressed data is retrieved based on the user data: and an output unit for decompressing retrieved data and outputting a decompressed data to the user.
摘要翻译：便携式语音/字母处理装置包括用于接收输入数据的输入单元：用于存储压缩数据的存储单元：用于产生控制信号的控制单元，以便根据用户数据检索压缩数据;以及输出单元，解压缩检索的数据并将解压缩的数据输出给用户。

7. 发明申请

US20040181400A1 Apparatus, methods and articles incorporating a fast algebraic codebook search technique 有权
标题翻译：包含快速代数码本搜索技术的装置，方法和文章
公开(公告)号：US20040181400A1
公开(公告)日：2004-09-16
申请号：US10387749
申请日：2003-03-13
申请人： Intel Corporation
发明人： Karthik Kannan , Meenakshi Sundaram Subramanian
IPC分类号： G10L019/12 , G10L021/00
CPC分类号： G10L19/107
摘要： An efficient method for codebook search, employed in speech coding, uses an optimal pulse-position grouping and a split track arrangement, based on a likelihood estimator. Also disclosed are codecs, mobile voice communication devices, telecommunications equipment and telecommunications methods.
摘要翻译：在语音编码中使用的用于码本搜索的有效方法使用基于似然估计器的最佳脉冲位置分组和分割轨道布置。还公开了编解码器，移动语音通信设备，电信设备和电信方法。

8. 发明申请

US20040172257A1 Speech-to-speech generation system and method 有权
标题翻译：语音到语音生成系统和方法
公开(公告)号：US20040172257A1
公开(公告)日：2004-09-02
申请号：US10683335
申请日：2003-10-10
申请人： International Business Machines Corporation
发明人： Shen Liqin , Shi Qin , Donald T. Tang , Zhang Wei
IPC分类号： G10L021/00
CPC分类号： G10L13/00 , G10L13/04
摘要： An expressive speech-to-speech generation system and method which can generate expressive speech output by using expressive parameters extracted from the original speech signal to drive the standard TTS system. The system comprises: speech recognition means, machine translation means, text-to-speech generation means, expressive parameter detection means for extracting expressive parameters from the speech of language A, and expressive parameter mapping means for mapping the expressive parameters extracted by the expressive parameter detection means from language A to language B, and driving the text-to-speech generation means by the mapping results to synthesize expressive speech. The system and method can improve the quality of the speech output of the translating system or TTS system.
摘要翻译：一种具有表现力的语音对语音生成系统和方法，可以通过使用从原始语音信号中提取的表现力参数来产生表达性语音输出来驱动标准TTS系统。该系统包括：语音识别装置，机器翻译装置，文本到语音生成装置，用于从语言A的语音中提取表达性参数的表现参数检测装置，以及用于映射表达参数提取的表现参数的表现参数映射装置从语言A到语言B的检测手段，并且通过映射结果来驱动文本到语音生成装置以合成表达性语音。系统和方法可以提高翻译系统或TTS系统语音输出的质量。

9. 发明申请

US20040153322A1 Menu-based, speech actuated system with speak-ahead capability 有权
标题翻译：基于菜单的语音启动系统具有先进的能力
公开(公告)号：US20040153322A1
公开(公告)日：2004-08-05
申请号：US10355126
申请日：2003-01-31
申请人： Comverse, Inc.
发明人： Marc J. Neuberger , Erin M. Panttaja
IPC分类号： G10L021/00
CPC分类号： G10L15/193
摘要： An interactive voice response system has speak-ahead capabilities similar to type-ahead IVR systems by determining multi-level grammars for responses. Preferably, an existing IVR application is processed automatically to generate a multi-level grammar database that can then be used in recognizing multi-level responses by a user.
摘要翻译：交互式语音应答系统通过确定响应的多级语法，具有与先进IVR系统类似的讲话功能。优选地，现有的IVR应用程序被自动处理以产生多级语法数据库，然后可以将其用于识别用户的多级响应。

10. 发明申请

US20040148175A1 Language learning system and a digital storage unit 有权
标题翻译：语言学习系统和数字存储单元
公开(公告)号：US20040148175A1
公开(公告)日：2004-07-29
申请号：US10479046
申请日：2004-02-23
发明人： Eero Nieminen , Timo Saarni
IPC分类号： G10L021/00
CPC分类号： G09B17/00 , G09B19/04
摘要： Audio recordings and programs are saved as audio files on a digital storage unit in a language learning system comprising student units connected to the digital storage unit. The digital storage unit is provided with a audio interface controller (201) having a dedicated input/output RAM buffer (B1-B63) for each student station. Each RAM buffer has an associated file which is either a fixed file or can be defined for each case. When the audio interface controller (201) receives a record command relating to a specific buffer, the controller (201) opens an audio file associated with the specific buffer, buffers the audio data received from a student station or another source in the buffer, and transfers the contents of the specified buffer to the opened associated audio file. Similarly, in response to a play command relating to a specific RAM buffer, the controller (201) opens an associated audio file in the digital storage unit, transfers audio data from the opened audio file to the buffer, and sends the audio data from the buffer to a respective student station or to other destination.

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