公开(公告)号：WO2007103041A2

公开(公告)日：2007-09-13

申请号：PCT/US2007/004974

申请日：2007-02-27

Applicant: PLANTRONICS, INC. ,  REUSS, Edward

Inventor： REUSS, Edward

IPC: G10L11/00 ,  H04M1/27

CPC classification number: H04R1/10 ,  G10L15/26 ,  H04M1/6066 ,  H04M2201/39 ,  H04M2201/40 ,  H04R5/033 ,  H04R2201/107 ,  H04R2420/07

Abstract: A wireless local area network system and a headset for the system. The headset uses voice-input information to set up parameters needed to connect the headset to the corresponding access point and then start the connection process. When the connection fails or succeeds appropriate voice prompt or visible signal tells the user the headset's connection status.

Abstract translation:

系统的无线局域网系统和耳机。 耳机使用语音输入信息来设置将耳机连接到相应接入点所需的参数，然后开始连接过程。 当连接失败或成功时，适当的语音提示或可见信号告诉用户耳机的连接状态。

公开(公告)号：WO2007059792A1

公开(公告)日：2007-05-31

申请号：PCT/EP2005/012692

申请日：2005-11-24

Applicant: TELEFONAKTIEBOLAGET LM ERICSSON (publ) ,  ROGIER, August, Caspar, Joseph, Noldus

Inventor： ROGIER, August, Caspar, Joseph, Noldus

IPC: H04M3/493 ,  H04M1/27

CPC classification number: H04M3/4931 ,  H04M3/4935

Abstract: The application relates to a network assisted calling service comprising a service call to an assistance entity which translates an indication of a destinatin party into a destination identifier which is subsequently used for the establishment of a user call between the calling and the destination party. In the prior art the user call has either to be set up manually by the calling terminal or it is set up by the network node to which the assistance entity is connected which suffers from disadvantages with respect to routing, complex charging schemes, etcetera. In the method of the invention, this is resolved by said destination identifier being returned through a signalling channel associated with the operative connection. The destination identifier is either returned to the calling party's terminal (C) or is returned to a network node (N) . Either the terminal (C) or the network node (N) subsequently set up the user call.

Abstract translation: 该应用涉及一种网络辅助呼叫服务，其包括向辅助实体的服务呼叫，该协助实体将目的地方的指示转换为目的地标识符，该目的地标识符随后用于在主叫与目的方之间建立用户呼叫。 在现有技术中，用户呼叫或者由主叫终端手动建立，或者由被连接的辅助实体的网络节点建立，该网络节点在路由，复合计费方案等方面存在缺点。 在本发明的方法中，由所述目的地标识符通过与所述操作连接相关联的信令信道返回来解决。 目的地标识符返回给主叫方的终端（C），或返回给网络节点（N）。 终端（C）或网络节点（N）随后建立用户呼叫。

公开(公告)号：WO2007020494A3

公开(公告)日：2007-02-22

申请号：PCT/IB2006/001993

申请日：2006-07-20

Applicant: NOKIA CORPORATION ,  NOKIA INC. ,  ISO-SIPILA, Juha

Inventor： ISO-SIPILA, Juha

IPC: H04M1/725 ,  H04M1/27

Abstract: The present invention concerns methods and apparatus for performing voice- controlled actions during an ongoing voice telephony session. In particular, the methods and apparatus of the present invention provide a voice-operated user interface to perform actions during an ongoing voice telephony session. Many of the actions that can be performed during the ongoing voice telephony session are context-sensitive and relate to the context of the telephone call. In addition, context information relating to the ongoing voice telephony session can be used to greatly simplify both the operation of the voice- controlled user interface and the programming of actions requested using the voice-controlled interface.

公开(公告)号：WO2005067277A3

公开(公告)日：2005-11-24

申请号：PCT/US2004038331

申请日：2004-11-16

Applicant: ELECTRONIC DATA SYST CORP ,  KARDOS CHRISTOPHER P

Inventor： KARDOS CHRISTOPHER P

IPC: H04M1/27 ,  H04M1/57 ,  H04M3/56

CPC classification number: H04M3/569 ,  H04M1/271 ,  H04M1/575 ,  H04M3/42042 ,  H04M3/56 ,  H04M2201/38

Abstract: Systems and techniques for identifying a participant in a teleconference allow other participants at remote locations to be informed of the identify of a current speaker. A currently speaking participant is identified in a teleconference conducted using a connection on a circuit-switched network, and a signal indicating an identifier of the currently speaking participant is transmitted over the connection on the circuit-switched network. The signal is received, and the identifier of the currently speaking participants is displayed at a participating location. The displayed identifier is determined based on the indication in the signal.

Abstract translation: 用于识别电话会议中的参与者的系统和技术允许向远程位置的其他参与者通知当前说话者的标识。 在使用电路交换网络上的连接进行的电话会议中识别现在的与会者，并且通过电路交换网络上的连接发送指示当前说话的参与者的标识符的信号。 接收到信号，并且在参与位置显示当前讲话的参与者的标识符。 所显示的标识符是根据信号中的指示确定的。

公开(公告)号：WO2005024779B1

公开(公告)日：2005-07-21

申请号：PCT/US2004024959

申请日：2004-07-30

Applicant: MATSUSHITA ELECTRIC IND CO LTD ,  JUNQUA JEAN-CLAUDE ,  KUHN ROLAND ,  CONTOLINI MATTEO ,  CHENGALVARAYAN RATHINAVELU

Inventor： JUNQUA JEAN-CLAUDE ,  KUHN ROLAND ,  CONTOLINI MATTEO ,  CHENGALVARAYAN RATHINAVELU

IPC: G10L15/08 ,  G10L15/10 ,  G10L15/22 ,  H04M1/27 ,  G10L15/00

CPC classification number: H04M1/271 ,  G10L15/08 ,  G10L15/10 ,  G10L15/22

Abstract: A method for improving recognition results of a speech recognizer uses supplementary information to confirm recognition results. A user inputs speech to a speech recognizer residing on a mobile device or on a server at a remote location. The speech recognizer determines a recognition result based on the input speech. A confidence measure is calculated for the recognition result. If the confidence measure is below a threshold, the user is prompted for supplementary data. The supplementary data is determined dynamically based on ambiguities between the input speech and the recognition result; the supplementary data distinguishes the input speech over potential incorrect results. The supplementary data may be a subset of alphanumeric characters that comprise the input speech, or other data associated with a desired result, such as an area code or location. The user may provide the supplementary data verbally, or manually using a keypad, touchpad, touchscreen, or stylus pen.

Abstract translation: 用于改进语音识别器的识别结果的方法使用补充信息来确认识别结果。 用户将语音输入驻留在移动设备上或远程位置处的服务器上的语音识别器。 语音识别器基于输入语音确定识别结果。 计算识别结果的置信度。 如果置信度测量值低于阈值，则提示用户输入补充数据。 补充数据是基于输入语音和识别结果之间的模糊度动态确定的; 补充数据区分输入语音和潜在错误结果。 补充数据可以是包括输入语音的字母数字字符的子集，或与期望结果相关的其他数据，例如区号或位置。 用户可以口头提供补充数据，或使用小键盘，触摸板，触摸屏或手写笔手动提供补充数据。

公开(公告)号：WO2004070493A2

公开(公告)日：2004-08-19

申请号：PCT/EP2004000322

申请日：2004-01-16

Applicant: SIEMENS AG ,  HOFFMANN GERHARD ,  VAN RIEK MAURICE

Inventor： HOFFMANN GERHARD ,  VAN RIEK MAURICE

IPC: G06F20060101 ,  G06F17/20 ,  G10L15/02 ,  G10L15/26 ,  H04M1/27 ,  H04M1/2745 ,  H04M3/493 ,  G06F

CPC classification number: G10L2015/228

Abstract: The vocabulary for a talker-independent name selection is updated by means of call lists.

Abstract translation: 扬声器独立名称拨号的词汇与通话记录进行更新。

公开(公告)号：WO2004036880A8

公开(公告)日：2004-06-17

申请号：PCT/US0327281

申请日：2003-08-29

Applicant: VOCERA COMMUNICATIONS INC

Inventor： SHOSTAK ROBERT E ,  RAINS WILLIAM A

IPC: H04L12/28 ,  H04L12/56 ,  H04M1/27 ,  H04M1/57 ,  H04M1/60 ,  H04M1/725 ,  H04M1/733 ,  H04M3/42 ,  H04W8/18 ,  H04M1/00

CPC classification number: H04W8/18 ,  G06F21/35 ,  H04M1/271 ,  H04M1/57 ,  H04M1/6041 ,  H04M1/725 ,  H04M1/72547 ,  H04M1/733 ,  H04M3/387 ,  H04M3/42 ,  H04M3/42068 ,  H04M3/42204 ,  H04M3/42314 ,  H04M3/42323 ,  H04M2203/2016 ,  H04M2207/18 ,  H04M2242/30 ,  H04M2250/02

Abstract: A wireless communication system has a central computer (36), one or more access points (34) and personal badges (32) that communicate with the one or more access points (34). The central computer (36) includes a database indexed by either user identification codes or badge serial numbers. When a user activates a badge (32), the central computer assigns the badge so that any message for the user is directed to the badge. The user may also access his personal data section in a central computer database through the badge (32) while the activation is valide. When the user deactivates the badge, the central computer (36) deletes the association and returns the badge (32) to a non-user-specific state. Where docking stations are available to rest the badges (32) not being used, the badges (32) may be configured so that they are activated when decoupled from the docking stations and deactivated when coupled to the docking stations.

Abstract translation: 无线通信系统具有与一个或多个接入点（34）通信的中央计算机（36），一个或多个接入点（34）和个人徽章（32）。 中央计算机（36）包括由用户标识码或徽章序列号索引的数据库。 当用户激活徽章（32）时，中央计算机分配徽章，使得用户的任何消息被引导到徽章。 用户还可以通过徽章（32）在中央计算机数据库中访问他的个人数据部分，同时激活是有效的。 当用户停用徽章时，中央计算机（36）删除关联并将徽章（32）返回到非用户特定状态。 在对接站可用于休息未使用的徽章（32）的情况下，可以配置徽章（32），使得当与对接站解耦时它们被激活，并且当耦合到对接站时被禁用。

公开(公告)号：WO2003107634A1

公开(公告)日：2003-12-24

申请号：PCT/EP2003/005855

申请日：2003-06-04

Applicant: SIEMENS AKTIENGESELLSCHAFT

Inventor： BAUER, Josef ,  HOFFMANN, Gerhard ,  SCHNEIDER, Tobias

IPC: H04M1/27

CPC classification number: H04M1/72547 ,  H04M1/271

Abstract: Die Erfindung betrifft ein Texteingabeverfahren für ein Kommunikationsendgerät mit einer Anzeigeeinrichtung, mindestens zwei Tastenfunktionen und einem Spracherkenner. Mit der ersten Tastenfunktion wird die Spracherkennung eingeleitet und als Ergebnis eine n-Bestliste der erkannten und bewerteten Eingabe auf der Anzeigeeinrichtung dargestellt, mit der zweiten Tastenfunktion erfolgt eine Auswahl in der n-Bestliste, und mit wiederum der ersten oder einer weiteren Tastenfunktion erfolgt eine Übernahme der ausgewählten Eingabe in einen Text.

Abstract translation: 本发明涉及一种用于具有显示装置的通信终端中的文本输入方法，至少两个键的功能和语音识别器。 与所述第一键功能，语音识别被启动，并且作为结果正Bestliste所示的显示装置上所识别的，并在额定输入，与所述第二键功能，在n Bestliste的选择，进而，在第一或进一步的关键功能是接管 所选择的输入到文本。

公开(公告)号：WO0178443A3

公开(公告)日：2003-10-16

申请号：PCT/US0111069

申请日：2001-04-05

Applicant: ARIALPHONE LLC

Inventor： PIRELLI THOMAS R ,  PATEL SANJEEV D ,  CYGNUS MARC W ,  SCHMID JOSEPH J ,  WAGENER MICHAEL E

IPC: G10L15/22 ,  H04B1/38 ,  H04M1/05 ,  H04M1/253 ,  H04M1/27 ,  H04M1/60 ,  H04M1/725 ,  H04R1/10 ,  H04R1/08

CPC classification number: H04M1/6066 ,  G10L15/22 ,  H04B1/385 ,  H04B2001/3866 ,  H04M1/05 ,  H04M1/2535 ,  H04M1/271 ,  H04M1/6033 ,  H04M1/725 ,  H04M2250/02 ,  H04R1/10 ,  H04R1/1025 ,  H04R1/1041 ,  H04R1/1066 ,  H04R2201/107 ,  H04R2420/07

Abstract: A system and method for providing wireless communication which is controlled by voice recognition software running on a controller. The system includes an earset communicator and a Base Station that allows wireless communication between these elements. The earset communicator rests comfortably on the user's ear and is held in place by an earhook. The transceiver Base Station communicates with the earset communicator and connects to a host controller, such as personal computer ("PC") or a household product, and to a network interface such as an internet connection or phone line. Voice commands are used for many functions for controlling the system. The Base Station routes the earset microphone audio to the controller software for speech recognition and command processing. Speech recognition software on the controller interprets the voice command and acts accordingly.

Abstract translation: 一种用于提供由控制器上运行的语音识别软件控制的无线通信的系统和方法。 该系统包括耳机通信器和允许这些元件之间的无线通信的基站。 耳环通讯器舒适地放在用户的耳朵上，并通过耳挂挂在适当位置。 收发机基站与耳机通信器通信，并连接到诸如个人计算机（“PC”）或家用产品的主机控制器，以及诸如因特网连接或电话线的网络接口。 语音命令用于许多用于控制系统的功能。 基站将耳机麦克风音频路由到控制器软件进行语音识别和命令处理。 控制器上的语音识别软件解释语音命令并相应地进行操作。

公开(公告)号：WO02054333A3

公开(公告)日：2002-11-21

申请号：PCT/IL0101221

申请日：2001-12-31

Applicant: POLY INFORMATION LTD ,  ALT OFER ,  RAPOPORT SIMON ,  SHAMIR OREN ,  KNYAZHANSKY ILYA

Inventor： ALT OFER ,  RAPOPORT SIMON ,  SHAMIR OREN ,  KNYAZHANSKY ILYA

IPC: G10L15/00 ,  G10L15/10 ,  H04M1/27

CPC classification number: G10L15/10 ,  G10L2015/085 ,  H04M1/271

Abstract: A verbal input sentence is received from the user in the SR system (102), and a weight is assigned for the level of match for each sentence from the plurality determined sentences according to the content of the input sentence. N (206) sentences having the highest weight are selected from the plurality. If the weight of at least one of the N (206)sentences is higher than the threshold, the sentence having the highest weight is output as the recognized input sentence. If the weight of each selected sentence is lower than the threshold, the weight of each selected sentence is varied according to different predetermined criteria. If the varied weight of at least one of the N (206) sentences is higher than the threshold, the sentence having the highest varied weight is output as the recognized input sentence (209), otherwise an indication that corresponds to unrecognized input sentence is provided.

Abstract translation: 在SR系统（102）中从用户接收到口头输入句，并且根据输入的句子的内容从多个确定的句子中为每个句子分配权重。 从多个中选择具有最高权重的N（206）个句子。 如果N（206）句中的至少一个的权重高于阈值，则输出具有最高权重的句子作为识别的输入句子。 如果每个所选句子的权重低于阈值，则每个选择的句子的权重根据不同的预定标准而变化。 如果N（206）句中的至少一个句子的变化权重高于阈值，则输出具有最高变化权重的句子作为识别的输入句子（209），否则提供对应于未被识别的输入句子的指示 。