公开(公告)号：WO2016048581A1

公开(公告)日：2016-03-31

申请号：PCT/US2015/047527

申请日：2015-08-28

Applicant: INTEL CORPORATION

Inventor： GRAFF, Peter ,  QUIRINO SIMOES, Ana Paula ,  NAKATSU, Crystal A. ,  CHRISTIAN, Jessica M.

IPC: G01C21/36 ,  G06F3/16 ,  G10L15/18 ,  G10L15/22

CPC classification number: G06F3/167 ,  G01C21/3641 ,  G10L13/033 ,  G10L13/043 ,  G10L15/1822 ,  G10L15/187 ,  G10L15/22 ,  G10L15/265 ,  G10L17/26 ,  G10L25/51 ,  G10L2015/223 ,  G10L2015/226

Abstract: Systems and methods for providing a user adaptive natural language interface are disclosed. The disclosed embodiments may receive and analyze user input to derive current user behavior data, including data indicative of characteristics of the user input. The user input is classified based on prior user behavior data previously logged during one or more previous user-system interactions and the current user behavior data to generate a classification of the user input. Machine learning algorithms can be employed to classify the user input. User adaptive utterances are selected based on the user input and the classification of the user input. The user-system interaction is logged for use as prior user behavior data in future user-system interactions. A response to the user input is generated, including synthesizing output speech from the user adaptive utterances selected. Example applications of the disclosed systems and methods provide user adaptive navigation directions in navigation systems.

Abstract translation: 公开了用于提供用户自适应自然语言接口的系统和方法。 所公开的实施例可以接收和分析用户输入以导出当前用户行为数据，包括指示用户输入的特征的数据。 用户输入基于先前在一个或多个先前用户 - 系统交互期间记录的先前用户行为数据和当前用户行为数据进行分类，以生成用户输入的分类。 机器学习算法可用于对用户输入进行分类。 基于用户输入和用户输入的分类来选择用户自适应语音。 用户系统交互记录用作未来用户系统交互中的先前用户行为数据。 产生对用户输入的响应，包括从所选择的用户自适应语音合成输出语音。 所公开的系统和方法的示例应用在导航系统中提供用户适应性导航方向。

公开(公告)号：WO2017108142A1

公开(公告)日：2017-06-29

申请号：PCT/EP2015/081243

申请日：2015-12-24

Applicant: INTEL CORPORATION ,  PEREZ, Guillermo

Inventor： PEREZ, Guillermo ,  SHELLEF, Eric Ariel ,  SHILON, Reshef ,  GRAFF, Peter ,  ENG, Jonathan ,  LUCAS, Juan Manuel ,  VAN DEN BERG, Martin Henk

IPC: G10L15/24

CPC classification number: G06F17/30032 ,  G06K2009/00939 ,  G10L15/075 ,  G10L15/183 ,  G10L15/24 ,  G10L17/02 ,  G10L17/22

Abstract: The present disclosure describes dynamically adjusting linguistic models for automatic speech recognition based on biometric information to produce a more reliable speech recognition experience. Embodiments include receiving a speech signal, receiving a biometric signal from a biometric sensor implemented at least partially in hardware, determining a linguistic model based on the biometric signal, and processing the speech signal for speech recognition using the linguistic model based on the biometric signal.

Abstract translation: 本公开描述了基于生物信息动态地调整用于自动语音识别的语言模型以产生更可靠的语音识别体验。 实施例包括：接收语音信号;从至少部分地以硬件实现的生物测量传感器接收生物测量信号;基于生物测量信号确定语言模型;以及基于生物测量信号使用语言模型处理语音信号以用于语音识别。

公开(公告)号：WO2016048582A1

公开(公告)日：2016-03-31

申请号：PCT/US2015/047534

申请日：2015-08-28

Applicant: INTEL CORPORATION

Inventor： CHRISTIAN, Jessica M. ,  GRAFF, Peter ,  NAKATSU, Crystal A. ,  HOCKEY, Beth Ann

IPC: G10L13/08

CPC classification number: G10L13/027 ,  G06F17/2785 ,  G06F17/28 ,  G10L13/08 ,  G10L2013/083

Abstract: Systems and methods are disclosed for providing non-lexical cues in synthesized speech. Original text is analyzed to determine characteristics of the text and/or to derive or augment an intent (e.g., an intent code). Non-lexical cue insertion points are determined based on the characteristics of the text and/or the intent. One or more non-lexical cues are inserted at insertion points to generate augmented text. The augmented text is synthesized into speech, including converting the non-lexical cues to speech output.

Abstract translation: 公开了用于在合成语音中提供非词法线索的系统和方法。 分析原始文本以确定文本的特征和/或导出或增加意图（例如，意图代码）。 非词汇提示插入点是基于文本的特征和/或意图来确定的。 在插入点插入一个或多个非词汇提示以产生增强文本。 扩展文本被合成为语音，包括将非词汇提示转换为语音输出。