公开(公告)号：US20210201696A1

公开(公告)日：2021-07-01

申请号：US16623814

申请日：2017-07-18

Applicant: Intel Corporation

Inventor： Guillermo Perez ,  Israel Perez Tudela ,  Manuel Castro

IPC: G09B19/04 ,  G09B5/06 ,  G10L25/57 ,  G10L25/60 ,  G10L25/63

Abstract: The system may include data gathering circuitry to collect audio, video, and biometric data generated by a speaker during a presentation. All or a portion of the collected audio, video, and biometric data may be stored or otherwise retained on one or more storage devices. All or a portion of the collected audio, video, and biometric data may be forwarded to the presentation analysis circuitry. The presentation analysis circuitry detects at least one of: an audio presentation event; a video presentation event; or a biometric presentation event based at least in part on the collected audio, video, and biometric data received from the data gathering circuitry. The presentation analysis circuitry forwards the detected audio presentation event; a video presentation event; or a biometric presentation event to the presenter feedback circuitry. The presenter feedback circuitry generates feedback for presentation to the speaker.

公开(公告)号：US20200243069A1

公开(公告)日：2020-07-30

申请号：US16650161

申请日：2017-11-15

Applicant: INTEL CORPORATION

Inventor： Gabriel Amores ,  Guillermo Perez ,  Moshe Wasserblat ,  Michael Deisher ,  Loic Dufresne de Virel

IPC: G10L15/06 ,  G10L15/16 ,  G10L15/183

Abstract: An apparatus for speech model with personalization via ambient context harvesting, is described herein. The apparatus includes a microphone, context harvesting module, confidence module, and training module. The context harvesting module is to determine a context associated with the captured audio signals. A confidence module is to determine a confidence of the context as applied to the audio signals. A training module is to train a neural network in response to the confidence being above a predetermined threshold.

公开(公告)号：US20180358021A1

公开(公告)日：2018-12-13

申请号：US15781229

申请日：2015-12-23

Applicant: Intel Corporation

Inventor： Meladel Mistica ,  Martin Henk Van Den Berg ,  Guillermo Perez ,  Robert Jim Firby ,  Beth Ann Hockey

IPC: G10L17/04 ,  G10L15/26 ,  G10L15/22

CPC classification number: G10L17/04 ,  G06F19/00 ,  G10L15/22 ,  G10L15/26 ,  G10L2015/225 ,  G16H40/63

Abstract: The present disclosure describes providing a biometric signal as an input to a dialog system. A biometric signal processor can derive contextual biometric information about the biometric signal based on stored information and received, user-provided information. The dialog system can be used to interface with a user to receive contextual data about the user's status or activities, and can be used to interact with the user to request information and provide the contextualized biometric information.

公开(公告)号：US20180185705A1

公开(公告)日：2018-07-05

申请号：US15396243

申请日：2016-12-30

Applicant: Intel Corporation

Inventor： Guillermo Perez ,  Israel Perez Tudela

IPC: A63B24/00 ,  A63B71/06

CPC classification number: G16H20/30 ,  G09B19/0038

Abstract: Systems, apparatuses and methods may provide for technology to improve a workout experience of a user by determining an emotional state of the user, identifying a workout route based on the emotional state of the user, and outputting the workout route via a user interface device. Additionally, determining the emotional state of the user may include inferring emotions from one or more sensor information or user speech information. In one example, the sensor information includes one or more of blood pressure signals, heart rate signals or sweat measurement signals and the user speech information includes one or more of words used in an input utterance or a prosody of the input utterance.

公开(公告)号：US20170177716A1

公开(公告)日：2017-06-22

申请号：US14979113

申请日：2015-12-22

Applicant: Intel Corporation

Inventor： Guillermo Perez ,  Manuel Castro ,  Israel Perez De Tudela

IPC: G06F17/30 ,  G10L15/22 ,  G06F17/27

CPC classification number: G06F16/35 ,  G06F16/24578 ,  G06F16/3344 ,  G06F16/90332 ,  G06F17/273 ,  G06F17/2785 ,  G06F17/279 ,  G10L15/26

Abstract: Technologies for interpreting an input from a user of a compute device are disclosed. The compute device may capture input data from, for example, a microphone. The compute device is configured to recognize the speech in the input data, and determines one or more semantic interpretations of the input data. The compute device ranks the semantic interpretations, and selects and applies one of the semantic interpretations. In ranking the semantic interpretations, the compute device may consider factors such as the dialogue history and the dialogue coherence of the semantic interpretations, as well as the confidence of how well each semantic interpretation matches the input data.