公开(公告)号：US08688452B2

公开(公告)日：2014-04-01

申请号：US11937410

申请日：2007-11-08

申请人： James Robert Lewis ,  Andrew Simpson ,  Peeyush Jaiswal

发明人： James Robert Lewis ,  Andrew Simpson ,  Peeyush Jaiswal

IPC分类号： G10L15/18 ,  G06F17/27

CPC分类号： G10L15/19

摘要： A computer-implemented method for dynamically generating a speech recognition grammar is provided. The method includes determining a target entry, and accessing a plurality of potential distracters. The method also includes selecting one or more distracters from the plurality of potential distracters. More particularly, each potential distracter selected is selected based upon an assessed acoustic dissimilarity between the distracter and the target entry. The method further includes dynamically generating a speech recognition grammar that includes the target entry and one or more of the distracters selected based upon an acoustic dissimilarity to the target entry.

摘要翻译： 提供了一种用于动态生成语音识别语法的计算机实现的方法。 该方法包括确定目标条目，以及访问多个潜在的干扰者。 该方法还包括从多个潜在干扰物中选择一个或多个分心器。 更具体地，基于分配器和目标入口之间的评估的声学差异来选择所选择的每个潜在的分配器。 该方法还包括动态生成语音识别语法，其包括目标条目和基于与目标条目的声学差异选择的一个或多个干扰器。

公开(公告)号：US20090125297A1

公开(公告)日：2009-05-14

申请号：US11937410

申请日：2007-11-08

申请人： James Robert Lewis ,  Andrew Simpson ,  Peeyush Jaiswal

发明人： James Robert Lewis ,  Andrew Simpson ,  Peeyush Jaiswal

IPC分类号： G06F17/27

CPC分类号： G10L15/19

摘要： A computer-implemented method for dynamically generating a speech recognition grammar is provided. The method includes determining a target entry, and accessing a plurality of potential distractors. The method also includes selecting one or more distractors from the plurality of potential distractors. More particularly, each potential distractor selected is selected based upon an assessed acoustic dissimilarity between the distractor and the target entry. The method further includes dynamically generating a speech recognition grammar that includes the target entry and one or more of the distractors selected based upon an acoustic dissimilarity to the target entry.

摘要翻译： 提供了一种用于动态生成语音识别语法的计算机实现的方法。 该方法包括确定目标条目，以及访问多个潜在的干扰物。 该方法还包括从多个潜在干扰物中选择一个或多个干扰物。 更具体地，基于在牵引器和目标入口之间的评估的声学差异来选择所选择的每个潜在的牵引器。 该方法还包括动态生成语音识别语法，其包括目标条目和基于与目标条目的声学差异选择的一个或多个干扰器。

公开(公告)号：US5815142A

公开(公告)日：1998-09-29

申请号：US576834

申请日：1995-12-21

申请人： David Joseph Allard ,  James Robert Lewis ,  Debra Ann Gawne Johnson ,  Francis James Canova, Jr. ,  Charles Sterling Lanier ,  William Villafana ,  Byron Kevin Tiller ,  Raymond Lee Yee ,  Julie Francis Goodwin ,  Jean Luter Stout ,  Peter Rowland Eastwood ,  Daniel Ming-Te Hsieh ,  Connie Yudip Au

发明人： David Joseph Allard ,  James Robert Lewis ,  Debra Ann Gawne Johnson ,  Francis James Canova, Jr. ,  Charles Sterling Lanier ,  William Villafana ,  Byron Kevin Tiller ,  Raymond Lee Yee ,  Julie Francis Goodwin ,  Jean Luter Stout ,  Peter Rowland Eastwood ,  Daniel Ming-Te Hsieh ,  Connie Yudip Au

IPC分类号： G06F3/14 ,  G06F3/033 ,  G06F3/041 ,  G06F3/048 ,  G06F15/02 ,  H04M1/02 ,  H04M1/247 ,  H04M1/27 ,  H04M1/2745 ,  H04M1/725 ,  H04N1/387 ,  H04Q7/32 ,  G09G5/00

CPC分类号： G06F3/04883 ,  G06F15/0225 ,  G06F3/0488 ,  H04M1/27455 ,  H04M1/72522 ,  H04M1/72547 ,  H04M1/72583 ,  H04M2250/22

摘要： In a personal communications device having a touch sensitive display screen, text may be marked by a user to be used with different applications. In particular, to begin marking, a user has to maintain his touch at a location on the screen for a short predetermined period of time until the system detects that the position is held over the same character for a delayed period, at which time the system beeps to provide an indication that there has been a change of operation mode. The marking mode continues in operation until the user removes his contact from the touch screen. Thus, text over which the contact point passes after the initiation of the marking mode is marked, until the user removes his contact point from the touch screen. A second beep is sounded to alert the user of the termination of the marking mode, and the appearance of a menu of operations on the screen. The menu of operations echoes the marked text for user confirmation. The marked text may be used by the user in a number of applications, among which include a calling application whereby the marked text is used to place a call.

摘要翻译： 在具有触敏显示屏的个人通信设备中，文本可由用户标记以与不同的应用一起使用。 特别地，为了开始标记，用户必须在屏幕上的一个位置保持他的触摸短暂的预定时间段，直到系统检测到该位置被保持在同一个字符上一段延迟的时间，此时系统 蜂鸣声提供操作模式改变的指示。 标记模式继续运行，直到用户从触摸屏中删除他的联系人。 因此，在标记模式开始之后接触点通过的文本被标记，直到用户从触摸屏上移除其接触点。 发出第二个蜂鸣声，提醒用户终止标记模式，并在屏幕上显示操作菜单。 操作菜单与标记的文本相呼应，以供用户确认。 标记的文本可以由用户在许多应用中使用，其中包括通过使用标记的文本来发出呼叫的呼叫应用。

公开(公告)号：US20120300917A1

公开(公告)日：2012-11-29

申请号：US13116103

申请日：2011-05-26

申请人： Patrick Michael Commarford ,  Lisa Seacat DeLuca ,  James Robert Lewis

发明人： Patrick Michael Commarford ,  Lisa Seacat DeLuca ,  James Robert Lewis

IPC分类号： H04M3/428

CPC分类号： H04M3/4285 ,  H04M3/5238

摘要： In one embodiment of the invention, a method for selecting hold music corresponding to an expected waiting time comprises establishing a communications link with a caller; marking a first event by placing the caller on hold; determining a waiting time between the first event and a second event; selecting a media file having a parameter corresponding to the determined waiting time; playing the media file over the established communications link to the caller; and re-determining a waiting time remaining until the second event, selecting a different media file having a parameter corresponding to the re-determined waiting time, and playing the different media file over the established communications link to the caller.

摘要翻译： 在本发明的一个实施例中，一种用于选择与预期等待时间相对应的保持音乐的方法包括建立与呼叫者的通信链路; 通过将呼叫者置于保持状态来标记第一个事件; 确定第一事件和第二事件之间的等待时间; 选择具有与所确定的等待时间对应的参数的媒体文件; 通过建立的通信链接播放媒体文件到呼叫者; 以及重新确定剩余的等待时间直到第二事件，选择具有与重新确定的等待时间相对应的参数的不同媒体文件，以及通过建立的通信链路播放不同的媒体文件给呼叫者。

公开(公告)号：US07356130B2

公开(公告)日：2008-04-08

申请号：US11026720

申请日：2004-12-30

申请人： Ciprian Agapi ,  Felipe Gomez ,  James Robert Lewis

发明人： Ciprian Agapi ,  Felipe Gomez ,  James Robert Lewis

IPC分类号： H04M1/64

CPC分类号： C23C16/4486 ,  C23C16/4481 ,  C23C16/4485 ,  C23C16/52

摘要： A wizard that from a fixed design can create various audio interfaces. The generated interfaces can be speech only, DTMF only, or various mixed speech and DTMF UIs. When specifying both speech and DTMF prompts, a number of combinations of these interfaces could be automatically generated. Robust speech recognition systems can be built by automatically generating a “shadow” DTMF application. The DTMF application will perform the same task as the primary speech application; however the transfer to a DTMF application could be done explicitly by the user, or could be transferred automatically (either a temporary or permanent transition) at a point in the call flow where there was a problem with the speech recognition.

摘要翻译： 从固定设计的向导可以创建各种音频接口。 生成的接口可以是仅语音，仅限DTMF，或者各种混合语音和DTMF UI。 当指定语音和DTMF提示时，可以自动生成这些接口的多个组合。 可以通过自动生成“影子”DTMF应用来构建强大的语音识别系统。 DTMF应用程序将执行与主要语音应用程序相同的任务; 然而，转移到DTMF应用程序可以由用户明确地完成，或者可以在语音识别出现问题的呼叫流程中的一个点自动传输（暂时或永久转换）。

公开(公告)号：US5708804A

公开(公告)日：1998-01-13

申请号：US686407

申请日：1996-07-26

申请人： Julie Francis Goodwin ,  Charles Sterling Lanier ,  James Robert Lewis ,  Byron Kevin Tiller ,  Raymond Lee Yee

发明人： Julie Francis Goodwin ,  Charles Sterling Lanier ,  James Robert Lewis ,  Byron Kevin Tiller ,  Raymond Lee Yee

IPC分类号： H04M1/247 ,  H04M1/2745 ,  H04M1/725 ,  G06F17/30 ,  H04M1/27

CPC分类号： H04M1/72583 ,  H04M1/27455 ,  H04M1/274558 ,  H04M1/72522 ,  Y10S707/922 ,  Y10S707/99933 ,  Y10S707/99935 ,  Y10S707/99936

摘要： A data processing device and method for searching a database having a plurality of entries to locate entries which match a search string. Each entry within the database is arranged into one or more predetermined search fields which each contain a character string. In response to receipt of a search string, a determination is made whether the search string is a subset of a particular entry within the database. In response to the determination that the search string is a subset of a particular entry, the particular entry is recorded as a matching entry. However, in response to a determination that the search string is not a subset of a particular entry, a determination is made whether a modified search string formed by removing delimiters from the search string is a subset of a character string within a particular predetermined search field within the particular entry. In response to a determination that the modified search string is a subset of the character string, the particular entry is recorded as a matching entry. Thereafter, the foregoing steps are repeated for each of the number of entries within the database such that matching entries within the database are efficiently located.

摘要翻译： 一种用于搜索具有多个条目的数据库以定位与搜索字符串匹配的条目的数据处理装置和方法。 数据库中的每个条目被排列成一个或多个预定的搜索字段，每个预定搜索字段包含字符串。 响应于接收到搜索字符串，确定搜索字符串是否是数据库内的特定条目的子集。 响应于搜索字符串是特定条目的子集的确定，特定条目被记录为匹配条目。 然而，响应于确定搜索字符串不是特定条目的子集，确定通过从搜索字符串中去除分隔符而形成的修改的搜索字符串是否是特定预定搜索字段内的字符串的子集 在特定条目内。 响应于修改的搜索字符串是字符串的子集的确定，特定条目被记录为匹配条目。 此后，针对数据库内的数量的条目重复上述步骤，使得数据库内的匹配条目被有效地定位。