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. 发明申请

US20140088964A1 Exemplar-Based Latent Perceptual Modeling for Automatic Speech Recognition 有权
标题翻译：用于自动语音识别的基于示例的潜在知觉建模
公开(公告)号：US20140088964A1
公开(公告)日：2014-03-27
申请号：US13626825
申请日：2012-09-25
申请人： APPLE INC.
发明人： Jerome Bellegarda
IPC分类号： G10L15/06
CPC分类号： G10L15/063
摘要： Methods, systems, and computer-readable media related to selecting observation-specific training data (also referred to as “observation-specific exemplars”) from a general training corpus, and then creating, from the observation-specific training data, a focused, observation-specific acoustic model for recognizing the observation in an output domain are disclosed. In one aspect, a global speech recognition model is established based on an initial set of training data; a plurality of input speech segments to be recognized in an output domain are received; and for each of the plurality of input speech segments: a respective set of focused training data relevant to the input speech segment is identified in the global speech recognition model; a respective focused speech recognition model is generated based on the respective set of focused training data; and the respective focused speech recognition model is provided to a recognition device for recognizing the input speech segment in the output domain.
摘要翻译：与从普通训练语料库中选择观察专用训练数据（也称为“观察特定范例”）有关的方法，系统和计算机可读介质，然后从观察专用训练数据中，公开了用于在输出域中识别观察的观察专用声学模型。一方面，基于初始训练数据集建立全局语音识别模型; 接收要在输出域中识别的多个输入语音段; 并且对于所述多个输入语音段中的每一个：在所述全局语音识别模型中识别与所述输入语音段相关的相应的一组聚焦训练数据; 基于相应的聚焦训练数据集合生成相应的聚焦语音识别模型; 并且将各个聚焦语音识别模型提供给用于识别输出域中的输入语音片段的识别装置。

2. 发明授权

US09760559B2 Predictive text input 有权
公开(公告)号：US09760559B2
公开(公告)日：2017-09-12
申请号：US14720655
申请日：2015-05-22
申请人： Apple Inc.
发明人： Jannes Dolfing , Brent Ramerth , Douglas Davidson , Jerome Bellegarda , Jennifer Moore , Andreas Eminidis , Joshua Shaffer
IPC分类号： G06F17/27
CPC分类号： G06F17/276 , G06F17/277
摘要： Systems and processes for predictive text input are provided. In one example process, a text input can be received. The text input can be associated with an input context. A frequency of occurrence of an m-gram with respect to a subset of a corpus can be determined using a language model. The subset can be associated with a context. A weighting factor can be determined based on a degree of similarity between the input context and the context. A weighted probability of a predicted text given the text input can be determined based on the frequency of occurrence of the m-gram and the weighting factor. The m-gram can include at least one word in the text input and at least one word in the predicted text.

3. 发明授权

US08935167B2 Exemplar-based latent perceptual modeling for automatic speech recognition 有权
标题翻译：用于自动语音识别的基于示例的潜在感知建模
公开(公告)号：US08935167B2
公开(公告)日：2015-01-13
申请号：US13626825
申请日：2012-09-25
申请人： Apple Inc.
发明人： Jerome Bellegarda
IPC分类号： G10L15/00 , G10L15/06
CPC分类号： G10L15/063
摘要： Methods, systems, and computer-readable media related to selecting observation-specific training data (also referred to as “observation-specific exemplars”) from a general training corpus, and then creating, from the observation-specific training data, a focused, observation-specific acoustic model for recognizing the observation in an output domain are disclosed. In one aspect, a global speech recognition model is established based on an initial set of training data; a plurality of input speech segments to be recognized in an output domain are received; and for each of the plurality of input speech segments: a respective set of focused training data relevant to the input speech segment is identified in the global speech recognition model; a respective focused speech recognition model is generated based on the respective set of focused training data; and the respective focused speech recognition model is provided to a recognition device for recognizing the input speech segment in the output domain.
摘要翻译：与从普通训练语料库中选择观察专用训练数据（也称为“观察特定范例”）有关的方法，系统和计算机可读介质，然后从观察专用训练数据中，公开了用于在输出域中识别观察的观察专用声学模型。一方面，基于初始训练数据集建立全局语音识别模型; 接收要在输出域中识别的多个输入语音段; 并且对于所述多个输入语音段中的每一个：在所述全局语音识别模型中识别与所述输入语音段相关的相应的一组聚焦训练数据; 基于相应的聚焦训练数据集合生成相应的聚焦语音识别模型; 并且将各个聚焦语音识别模型提供给用于识别输出域中的输入语音片段的识别装置。

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