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. 发明授权

US08606582B2 Multimodal disambiguation of speech recognition 有权
标题翻译：语音识别的多模式消歧
公开(公告)号：US08606582B2
公开(公告)日：2013-12-10
申请号：US13651258
申请日：2012-10-12
申请人： Nuance Communications, Inc.
发明人： Michael Longe , Richard Eyraud , Keith C. Hullfish
IPC分类号： G10L15/00 , G10L15/18
CPC分类号： G10L15/18 , G10L15/24 , G10L15/32
摘要： The present invention provides a speech recognition system combined with one or more alternate input modalities to ensure efficient and accurate text input. The speech recognition system achieves less than perfect accuracy due to limited processing power, environmental noise, and/or natural variations in speaking style. The alternate input modalities use disambiguation or recognition engines to compensate for reduced keyboards, sloppy input, and/or natural variations in writing style. The ambiguity remaining in the speech recognition process is mostly orthogonal to the ambiguity inherent in the alternate input modality, such that the combination of the two modalities resolves the recognition errors efficiently and accurately. The invention is especially well suited for mobile devices with limited space for keyboards or touch-screen input.
摘要翻译：本发明提供一种与一个或多个替代输入模式相结合的语音识别系统，以确保有效和准确的文本输入。语音识别系统由于处理能力有限，环境噪声和/或说话风格的自然变化而实现的精度不够完美。替代输入模式使用消歧或识别引擎来补偿减少的键盘，马虎输入和/或书写风格的自然变化。语音识别过程中残留的模糊度主要与交替输入模态中固有的歧义正交，从而两种模态的组合有效且准确地解决了识别错误。本发明特别适用于键盘空间有限或触摸屏输入的移动设备。

2. 发明申请

US20140372345A1 CONTEXTUAL PREDICTION OF USER WORDS AND USER ACTIONS 审中-公开
标题翻译：用户词汇和用户行为的相关预测
公开(公告)号：US20140372345A1
公开(公告)日：2014-12-18
申请号：US14472279
申请日：2014-08-28
申请人： NUANCE COMMUNICATIONS, INC.
发明人： Ethan R. BRADFORD , David J. Kay , Michael Longe , Pim Van Meurs , Gaurav Tandon
IPC分类号： G06N5/04 , G06N99/00 , G06F3/0482
CPC分类号： G06F17/276 , G06F3/0481 , G06F3/0482 , G06F9/45512 , G06N5/04 , G06N99/005 , H04M1/72566 , H04M1/72569 , H04M1/72572 , H04M2250/10
摘要： An operating sequence for a handheld computing device manages the device to automatically detect cues describing the device's environmental and user actions performed with the device, learn which cues and cue combinations are relevant to predict user actions, and then in response to occurrence of the relevant cues, predictively implementing the appropriate user action or configuring the device in anticipation of user action.
摘要翻译：手持式计算设备的操作顺序管理该设备以自动检测描述该设备的环境和用户操作的提示，该设备执行该设备，了解哪些提示和提示组合与预测用户动作相关，然后响应相关提示的发生，预期实施适当的用户动作或配置设备以预期用户动作。

3. 发明授权

US09626355B2 Contextual prediction of user words and user actions 有权
公开(公告)号：US09626355B2
公开(公告)日：2017-04-18
申请号：US14472279
申请日：2014-08-28
申请人： NUANCE COMMUNICATIONS, INC.
发明人： Ethan R. Bradford , David J. Kay , Michael Longe , Pim Van Meurs , Gaurav Tandon
IPC分类号： G06F3/00 , G06F3/048 , G06F17/27 , G06F3/0481 , G06F9/455 , G06F3/0482 , G06N5/04 , G06N99/00 , G06F3/14 , G06F17/00 , G06F15/00 , G06E1/00 , H04M1/725
CPC分类号： G06F17/276 , G06F3/0481 , G06F3/0482 , G06F9/45512 , G06N5/04 , G06N99/005 , H04M1/72566 , H04M1/72569 , H04M1/72572 , H04M2250/10
摘要： An operating sequence for a handheld computing device manages the device to automatically detect cues describing the device's environmental and user actions performed with the device, learn which cues and cue combinations are relevant to predict user actions, and then in response to occurrence of the relevant cues, predictively implementing the appropriate user action or configuring the device in anticipation of user action.

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