专利快速检索-快速检索全球专利，免费商用专利数据库-IPRDB

31. 发明申请

WO03061227A2 METHOD AND APPARATUS FOR DELIVERING MESSAGES BASED ON USER PRESENCE, PREFERENCE OR LOCATION 审中-公开
标题翻译：基于用户存在，偏好或位置传递消息的方法和装置
公开(公告)号：WO03061227A2
公开(公告)日：2003-07-24
申请号：PCT/US0301316
申请日：2003-01-15
申请人： AVAYA TECHNOLOGY CORP
发明人： KHAKOO SHABBIR A , KRISHNASWAMY VENKATESH , SIDDIQUI ANWAR A , ZENNER HAL B
IPC分类号： G10L13/04 , H04L12/58 , H04M3/53 , G06F17/60 , H04M3/533
CPC分类号： G10L13/00 , H04L51/04 , H04L51/066 , H04M3/42348 , H04M3/5307 , H04M3/5322 , H04M2201/60 , H04M2203/2016 , H04M2203/2066 , H04M2203/4536
摘要： A method and apparatus are disclosed for delivering messages to one or more intended recipients based on the presence, preferences or location of the recipients. Text-based messages, such as instant messages, can be delivered to one or more intended recipients by means of i a voice call to a voice-capable device associated with the recipients ii a voice mail message to a voice mail box associated with the recipients or iii a text or voice message, as appropriate, that is delivered upon the availability of one or more intended recipients. An instant message originating as a text message is converted to speech, if necessary, before being delivered to the intended recipient. The speech corresponding to the text of the message is played out once the call is answered or once the voice mail message is retrieved. The invention thus enables the delivery of messages to be routed and scheduled based on the location and availability of the intended recipient.
摘要翻译：公开了一种用于基于接收者的存在，偏好或位置将消息传递给一个或多个预期接收者的方法和装置。基于文本的消息（例如即时消息）可以通过对与接收者相关联的具有语音能力的设备的语音呼叫传递给一个或多个预期的接收者，语音邮件消息发送到与接收者相关联的语音信箱，或者 iii酌情提供根据一个或多个预期接收者的可用性提供的文本或语音消息。如果需要，将被发送为文本消息的即时消息在被传送到预期接收者之前被转换成语音。一旦呼叫被应答或一旦检索到语音邮件消息，就会播放与消息文本相对应的语音。因此，本发明使得能够基于预期接收者的位置和可用性来传送要路由和调度的消息。

32. 发明申请

WO0227708A3 CALL PROCESSING SYSTEM WITH INTERACTIVE VOICE RESPONSE 审中-公开
标题翻译：具有互动语音响应的呼叫处理系统
公开(公告)号：WO0227708A3
公开(公告)日：2002-08-08
申请号：PCT/US0129911
申请日：2001-09-25
申请人： HAVOVER COMM
发明人： PALACIOS JOSEPH R , ANGIA RAMCHAND , EDWARDS KENNETH
IPC分类号： G10L13/04 , G10L15/26 , H04M3/12 , H04M3/493 , H04M3/51 , H04M1/64
CPC分类号： G10L13/00 , G10L15/26 , H04M3/12 , H04M3/493 , H04M3/5158 , H04M3/5166 , H04M2201/40
摘要： A call processing system has an architecture that provides interactive voice response to callers before further routing of calls. Ports connected to the telephone network are coupled to processors that perform interactive voice response without a distributive switch therebetween, Redundancy is provided at component and system level and an uniterruptible power supply and transfer panel are connected to a supplemental generator. Local call processing systems are connected by multiple networks to remote call processing systems with a redundant distributed database accessible to the processors and resource servers for providing other services, such as text-to-speech and speech recognition. A resource management unit detects, stores and reports resources available on each system to higher level call processing systems connected via the network. Addresses of call processing systems at least at higher levels are accessible by a local call processing system for redundancy.
摘要翻译：呼叫处理系统具有在进一步路由呼叫之前向呼叫者提供交互式语音响应的架构。连接到电话网络的端口耦合到执行交互式语音响应而不在其间进行分配交换的处理器，在组件和系统级别提供冗余，并且单元可逆电源和传输面板连接到补充发电机。本地呼叫处理系统通过多个网络连接到远程呼叫处理系统，具有可由处理器和资源服务器访问的冗余分布式数据库，用于提供其他服务，例如文本到语音和语音识别。资源管理单元检测，存储和报告每个系统上可用的资源到通过网络连接的较高级别的呼叫处理系统。至少在较高级别的呼叫处理系统的地址可由本地呼叫处理系统进行冗余。

33. 发明申请

WO02049003A1 METHOD AND SYSTEM FOR CONVERTING TEXT TO SPEECH 审中-公开
标题翻译：方法和系统，用于将文本到语音
公开(公告)号：WO02049003A1
公开(公告)日：2002-06-20
申请号：PCT/DE2001/004658
申请日：2001-12-11
IPC分类号： G10L13/04 , H04M1/725 , G10L13/02
CPC分类号： G10L13/04 , H04M1/72547 , H04M1/72563
摘要： The aim of the invention is to have texts that are present in electronic form individually read out or replayed by way of the so-called "text-to-speech" technology. To this end, voice parameters (SD) are transmitted together with the text (TD) present in electronic form to a receiving unit (2) provided for replaying the text (TD). Said receiving unit (2) converts the received text (TD) to speech using the voice parameters (SD) received together with the text. The invention makes it possible to have texts, for example SMS messages or e-mails, which are present in electronic form read out with the voice of the sender.
摘要翻译：对于个人读取或通过所谓的“文本 - 语音”技术的装置以电子形式的文本再现，本发明提出，随着以电子形式的文本（TD）语音参数（SD）与一个共同（用于再现文本发送TD）预期的接收单元（2），其中所述接收单元（2）使用接收到的文本（TD）与文本语音参数（SD）成语音接收到一起。以这种方式，文本以电子形式作为可能的，例如，SMS消息或电子邮件，与发送者的声音读出。

34. 发明申请

WO02021090A1 A POINT-OF-SALE COMMERCIAL TRANSACTION PROCESSING SYSTEM USING ARTIFICIAL INTELLIGENCE ASSISTED BY HUMAN INTERVENTION 审中-公开
标题翻译：使用人为干预协助的人工智能的销售点商业交易处理系统
公开(公告)号：WO02021090A1
公开(公告)日：2002-03-14
申请号：PCT/US2001/028675
申请日：2001-09-10
IPC分类号： G07F9/02 , G10L13/04 , G10L15/26 , H04L12/58 , G01L9/00
CPC分类号： G10L13/00 , G07F9/02 , G10L15/26
摘要： A point-of-sale commercial transaction processing system, particularly suitable for the fast food industry, is provided. The transaction processing system (14) utilizes a customer interaction terminal (CIT, 12) having a video display (46), an audio speaker (42), a microphone (44), and preferably a printer; a computer system in communication with the CIT and running artificial intelligence routines to process verbal request provided into the microphone; and a human-controlled response system in communication with the computer system which completes, corrects or verifies requests that cannot be satisfactorily completed by artificial intelligence routines alone. The human-controlled response system is preferably in communication with the CIT and the customer via a high speed network connection.
摘要翻译：提供了特别适合快餐行业的销售点商业交易处理系统。交易处理系统（14）利用具有视频显示器（46），音频扬声器（42），麦克风（44）和优选地打印机的客户交互终端（CIT，12）与CIT通信并运行人工智能程序以处理提供给麦克风的口头请求的计算机系统; 以及与计算机系统通信的人为受控的响应系统，其完成，修正或验证仅由人工智能程序不能令人满意地完成的请求。人控制的响应系统优选地通过高速网络连接与CIT和客户进行通信。

35. 发明申请

WO01093247A1 SPEECH SYNTHESIS FROM INTERPOLATED VOICES 审中-公开
标题翻译：来自内部声音的语音合成
公开(公告)号：WO01093247A1
公开(公告)日：2001-12-06
申请号：PCT/GB2001/002385
申请日：2001-05-30
IPC分类号： G10L13/04 , G10L21/013 , G10L13/02
CPC分类号： G10L13/04 , G10L2021/0135
摘要： There is disclosed a method and apparatus for providing signals for a synthetic voice by way of derived voice-representative data. In embodiments of the invention, the derived data is derived (63) by combination of data representative of first and second (and maybe more) voices (61) of a base repertoire, the combined data including selected parameters of a formant-type voice synthesiser (30, 45). Combination may take place by interpolation between or extrapolation beyond the voices of the base repertoire. Individual parameters within the derived data may contain different proportions of corresponding parameters of the base repertoire. The invention is applicable either directly to control parameters of a synthesiser or to tables for these parameters.
摘要翻译：公开了一种用于通过派生语音代表数据提供用于合成语音的信号的方法和装置。在本发明的实施例中，通过组合表示基本曲目的第一和第二（也可能更多）个语音（或多个）语音（61）的数据的组合导出导出数据（63），该组合数据包括共振峰型语音合成器（30,45）。组合可以通过基础曲目的声音之间的插值或外推来进行。派生数据中的各个参数可能包含不同比例的基本曲目的相应参数。本发明可以直接用于控制合成器的参数或这些参数的表。

36. 发明申请

WO01082290A1 REMOTE-CONTROLLED SOUND REPRODUCING SYSTEM OF TEXT DATA STORED IN A MEMORY AND CONTROL METHOD THEREFOR 审中-公开
标题翻译：存储在其中的文本数据的远程控制声音再现系统及其控制方法
公开(公告)号：WO01082290A1
公开(公告)日：2001-11-01
申请号：PCT/KR2001/000580
申请日：2001-04-06
IPC分类号： A63H29/00 , G10L13/04 , G10L13/00
CPC分类号： G10L13/00
摘要： The present invention provides a remote-controlled sound reproducing system of text data stored in a memory, comprising a transmitter module for converting the text data stored in the memory into sound signals and for radio-transmitting the sound signals, and a receiver module for receiving the signals radio-transmitted from the transmitter module and for outputting sound corresponding thereto, whereby the text data stored in the memory is converted into the sound signals and radio-transmitted through the transmitter module to the receiver module and the sound signals received by the receiver module are converted into the sound to be outputted, so that a user located at a remote place can audibly confirm the contents of the texts displayed on a computer monitor. The present invention also provides a control method for a remote-controlled sound reproducing system of text data stored in a memory.
摘要翻译：本发明提供了一种存储在存储器中的文本数据的远程控制声音再现系统，包括：发送器模块，用于将存储在存储器中的文本数据转换成声音信号和用于无线电发送声音信号;以及接收器模块，用于接收从发射机模块发送的信号和用于输出与之对应的声音的信号，由此存储在存储器中的文本数据被转换成声音信号，并通过发射机模块无线电发送到接收机模块，并且由接收机接收的声音信号模块被转换为要输出的声音，使得位于远处的用户可以可听见地确认显示在计算机监视器上的文本的内容。本发明还提供了一种用于存储在存储器中的文本数据的遥控声音再现系统的控制方法。

37. 发明申请

WO01075555A2 PERSONAL VIRTUAL ASSISTANT 审中-公开
标题翻译：个人虚拟助理
公开(公告)号：WO01075555A2
公开(公告)日：2001-10-11
申请号：PCT/US2001/006883
申请日：2001-03-05
IPC分类号： G10L13/04 , G10L15/26 , G06F
CPC分类号： G10L13/00 , G10L15/26
摘要： A computer-based virtual assistant (100) the behaviour of which can be changed by the user. The virtual assistant comprises a voice user interface for inputing information into and receiving information from the virtual assistant by speech (110), communications network (104), and a virtual assistant application running on a remote computer. The remote computer is electronically coupled to the user interface via the communications network. The virtual assistant changes behaviour responsive to user input. The virtual assistant also automatically adapts its behavior.
摘要翻译：基于计算机的虚拟助理（100），其行为可以由用户改变。虚拟助理包括用于通过语音（110），通信网络（104）以及在远程计算机上运行的虚拟助理应用程序向虚拟助理输入信息并从其接收信息的语音用户界面。远程计算机通过通信网络电子耦合到用户接口。虚拟助手根据用户输入改变行为。虚拟助手还可以自动调整其行为。

38. 发明申请

WO01057851A1 SPEECH SYSTEM 审中-公开
标题翻译：语音系统
公开(公告)号：WO01057851A1
公开(公告)日：2001-08-09
申请号：PCT/AU2001/000111
申请日：2001-02-02
IPC分类号： G10L13/00 , G10L13/04 , G10L13/02
CPC分类号： G10L13/00
摘要： A system for generating an audio message over a communications network (4) that is at least partly in a voice representative of a character generally recognisable to a user. Either a voice message or text based message may be used to construct the audio message. Specific recordings of well known characters is stored in a storage means (14, 213) and background sound effects can be inserted into the audio message which are stored in database (14, 215). The audio message is constructed by any one of the processing means (12, 212, 214) and transmitted to a recipient for play back on a processing terminal.
摘要翻译：一种用于通过通信网络（4）产生音频消息的系统，所述通信网络至少部分地是代表用户通常可识别的角色的语音。可以使用语音消息或基于文本的消息来构造音频消息。众所周知的字符的特定记录被存储在存储装置（14,213）中，并且可以将背景声音效果插入到存储在数据库（14,215）中的音频消息中。音频消息由处理装置（12,212,214）中的任何一个构成，并被发送到接收者以便在处理终端上重放。

39. 发明申请

WO01033549A1 ELECTRONIC MAIL READING DEVICE AND METHOD, AND RECORDED MEDIUM FOR TEXT CONVERSION 审中-公开
标题翻译：电子邮件读取装置和方法，以及用于文本转换的记录介质
公开(公告)号：WO01033549A1
公开(公告)日：2001-05-10
申请号：PCT/JP2000/007652
申请日：2000-10-30
IPC分类号： G06F3/16 , G10L13/04 , H04L12/58 , G10L13/08 , G06F13/00 , G10L13/06
CPC分类号： H04L51/063 , G06F3/16 , G10L13/00
摘要： A text shaping unit (101) of an electronic mail reading device analyzes the format of a quoted portion of the text part of an electronic mail text and deletes quoting symbols so as to shape the quoted portion into a text of a format in units of one sentence. During this processing, command tags for commanding reading out loud before and after the quoted portion are inserted. A text converting unit (105) conducts text-conversion from a difficult-to-understand expression to an easy-to-understand expression. During this processing, command tags are also inserted before and after the converted portion. A speech synthesizing unit (108) synthesizes a speech of the text according to the command tags while controlling the speech synthesization, thus eventually converting an electronic mail text to an easy-to-understand speech.
摘要翻译：电子邮件阅读装置的文本整形单元（101）分析电子邮件文本的文本部分的引用部分的格式，并删除引用符号，以将被引用的部分形成格式的文本，其格式为1 句子。在该处理期间，插入用于在引用部分之前和之后大声读出的命令标签。文本转换单元（105）从难以理解的表达进行文本转换为易于理解的表达。在此处理期间，还会在转换部分之前和之后插入命令标签。语音合成单元（108）在控制语音合成的同时，根据命令标签合成文本的语音，从而最终将电子邮件文本转换为易于理解的语音。

40. 发明申请

WO0055842A3 SPEECH SYNTHESIS 审中-公开
标题翻译：语音合成
公开(公告)号：WO0055842A3
公开(公告)日：2000-12-21
申请号：PCT/GB0000854
申请日：2000-03-08
申请人： BRITISH TELECOMM , MINNIS STEPHEN
发明人： MINNIS STEPHEN
IPC分类号： G10L13/04 , G10L13/10
CPC分类号： G10L13/10 , G10L13/04
摘要： Conventional methods of predicting phrase boundaries occasionally result in the output of text-to-speech conversion apparatus sounding unnatural. Text-to-speech conversion apparatus described herein uses pattern-matching to predict the position of phrase boundaries in its spoken output. The apparatus analyses text input to the apparatus to identify groups of words (known as "chunks") which are unlikely to contain internal phrase boundaries. Both the chunks and individual words are labelled with their syntactic characteristics. The apparatus has access to a database of sentences which also contains such syntactic labels, together with indications of where a human reader would insert minor and major phrase boundaries. The parts of the database which have the most similar syntactic characteristics are found and phrase boundaries are predicted based on the phrase boundaries found in those parts. Other characteristics are also used in the pattern-matching process.
摘要翻译：常规的预测短语边界的方法偶尔导致文本到语音转换装置的输出听起来不自然。本文描述的文本到语音转换装置使用模式匹配来预测其口语输出中的短语边界的位置。该装置分析输入到装置的文本，以识别不太可能包含内部短语边界的单词组（称为“大块”）。这些块和单个单词都标有句法特征。该装置可以访问还包含这样的句法标签的句子数据库，以及人类读者在哪里插入小的和主要的短语边界的指示。找到具有最相似语法特征的数据库的部分，并且基于在这些部分中发现的短语边界来预测短语边界。其他特征也用于模式匹配过程。

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