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

US08600746B1 Speech recognition parameter adjustment 有权
标题翻译：语音识别参数调整
公开(公告)号：US08600746B1
公开(公告)日：2013-12-03
申请号：US13649747
申请日：2012-10-11
申请人： Google Inc.
发明人： Xin Lei , Patrick An Nguyen
IPC分类号： G10L15/26 , G10L15/00
CPC分类号： G10L15/22 , G10L15/30 , G10L2015/226
摘要： Audio data that encodes an utterance of a user is received. It is determined that the user has been classified as a novice user of a speech recognizer. A speech recognizer setting is selected that is used by the speech recognizer in generating a transcription of the utterance. The selected speech recognizer setting is different than a default speech recognizer setting that is used by the speech recognizer in generating transcriptions of utterances of users that are not classified as novice users. The selected speech recognizer setting results in increased speech recognition accuracy in comparison with the default setting. A transcription of the utterance is obtained that is generated by the speech recognizer using the selected setting.
摘要翻译：接收到编码用户话语的音频数据。确定用户已经被分类为语音识别器的新手用户。选择语音识别器设置，其由语音识别器用于产生话语的转录。所选择的语音识别器设置不同于语音识别器在生成未分类为新手用户的用户的话语的转录中使用的默认语音识别器设置。与默认设置相比，所选择的语音识别器设置导致语音识别精度提高。获得由语音识别器使用所选择的设置产生的话语的转录。

2. 发明授权

US09558743B2 Integration of semantic context information 有权
标题翻译：语义语境信息的整合
公开(公告)号：US09558743B2
公开(公告)日：2017-01-31
申请号：US13863505
申请日：2013-04-16
申请人： Google Inc.
发明人： Noah B. Coccaro , Patrick An Nguyen
IPC分类号： G10L15/00 , G10L15/16 , G10L15/18 , G10L25/30
CPC分类号： G10L15/1815 , G10L15/1822 , G10L25/30
摘要： In one implementation, a computer-implemented method includes receiving, at a computer system, a request to predict a next word in a dialog being uttered by a speaker; accessing, by the computer system, a neural network comprising i) an input layer, ii) one or more hidden layers, and iii) an output layer; identifying the local context for the dialog of the speaker; selecting, by the computer system and using a semantic model, at least one vector that represents the semantic context for the dialog; applying input to the input layer of the neural network, the input comprising i) the local context of the dialog and ii) the values for the at least one vector; generating probability values for at least a portion of the candidate words; and providing, by the computer system and based on the probability values, information that identifies one or more of the candidate words.
摘要翻译：在一个实现中，计算机实现的方法包括在计算机系统处接收用于预测由扬声器发出的对话中的下一个字的请求; 由计算机系统访问包括i）输入层，ii）一个或多个隐藏层，以及iii）输出层的神经网络; 识别演讲者对话的本地语境; 由计算机系统和使用语义模型选择表示对话的语义上下文的至少一个向量; 将输入应用于所述神经网络的输入层，所述输入包括i）所述对话的本地上下文，以及ii）所述至少一个向量的值; 为所述候选词的至少一部分生成概率值; 以及通过计算机系统并基于概率值提供标识一个或多个候选词的信息。

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