公开(公告)号：US20250104861A1

公开(公告)日：2025-03-27

申请号：US18665282

申请日：2024-05-15

Applicant: Apple Inc.

Inventor： Hamidreza ABBASPOURAZAD ,  Udhyakumar NALLASAMY ,  Oussama ELACHQAR ,  Saba EMRANI ,  Andrew MILLER ,  Ian R. SHAPIRO

IPC: G16H50/20 ,  G16H10/60

Abstract: The subject technology provides for large-scale training of foundation models for physiological signals from wearable electronic devices. An apparatus receives receive input data having a plurality of physiological signal information segments associated with a user. The apparatus applies one or more augmentation functions to the plurality of physiological signal information segments to generate an augmented version of the plurality of physiological signal information segments. The apparatus trains a neural network to produce a trained machine learning model by generating, via an encoder, an embedding of the augmented version having a first number of dimensions in an embedding space. The apparatus maps, via a multilayer perceptron projection, the embedding into a representation having a second number of dimensions. The apparatus determines mutual information between a pair of representations of the augmented version. The apparatus can deploy the trained machine learning model to predict a physiological state of the user.

公开(公告)号：US20160358600A1

公开(公告)日：2016-12-08

申请号：US14846650

申请日：2015-09-04

Applicant: Apple Inc.

Inventor： Udhyakumar NALLASAMY ,  Sachin S. KAJAREKAR ,  Matthias PAULIK ,  Matthew SEIGEL

IPC: G10L15/07 ,  G10L15/10 ,  G10L15/16

CPC classification number: G10L15/07 ,  G10L15/063 ,  G10L15/10 ,  G10L15/16 ,  G10L25/51 ,  G10L2015/0631

Abstract: Systems and processes for automatic accent detection are provided. In accordance with one example, a method includes, at an electronic device with one or more processors and memory, receiving a user input, determining a first similarity between a representation of the user input and a first acoustic model of a plurality of acoustic models, and determining a second similarity between the representation of the user input and a second acoustic model of the plurality of acoustic models. The method further includes determining whether the first similarity is greater than the second similarity. In accordance with a determination that the first similarity is greater than the second similarity, the first acoustic model may be selected; and in accordance with a determination that the first similarity is not greater than the second similarity, the second acoustic model may be selected.

Abstract translation: 提供了自动重音检测的系统和过程。 根据一个示例，一种方法包括在具有一个或多个处理器和存储器的电子设备处接收用户输入，确定用户输入的表示与多个声学模型的第一声学模型之间的第一相似度， 以及确定所述用户输入的表示与所述多个声学模型的第二声学模型之间的第二相似度。 该方法还包括确定第一相似度是否大于第二相似度。 根据第一相似度大于第二相似度的确定，可以选择第一声学模型; 并且根据第一相似度不大于第二相似度的确定，可以选择第二声学模型。

公开(公告)号：US20240379209A1

公开(公告)日：2024-11-14

申请号：US18237875

申请日：2023-08-24

Applicant: Apple Inc.

Inventor： Udhyakumar NALLASAMY ,  Nicholas FOTI ,  Julie A. ARNEY ,  Cecilia A. COOPER ,  Lessa WAKUTSU ,  Tahneetra CROSBY ,  Sean W. JEWELL ,  Varun MAUDGALYA ,  Troy J. CHEVALIER ,  Yujie LI ,  Lisa A. WHEELER

IPC: G16H20/30

Abstract: The subject system may be implemented by a processor circuit configured to receive a request for generating a workout schedule that includes one or more workout sessions and one or more workout content items associated with the one or more workout sessions. The request includes one or more workout session preferences and one or more workout content preferences. The processor circuit is configured to generate a schedule framework based on the one or more workout session preferences, the schedule framework comprising one or more scheduled workout sessions on one or more days of a week, generate the workout schedule by selecting, for each respective scheduled workout session in the schedule framework, a workout content item from a set of workout content items based at least in part on the one or more workout content preferences, and provide an indication of at least a portion of the workout schedule.

公开(公告)号：US20190303442A1

公开(公告)日：2019-10-03

申请号：US16024475

申请日：2018-06-29

Applicant: Apple Inc.

Inventor： Stephan PEITZ ,  Udhyakumar NALLASAMY ,  Matthias PAULIK ,  Yun TANG

IPC: G06F17/28 ,  G10L15/22 ,  G10L15/18

Abstract: Systems and processes for operating an electronic device to train a machine-learning translation system are described. In one process, a first set of training data is obtained. The first set of training data includes at least one payload in a first language and a translation of the at least one payload in a second language. The process further includes obtaining one or more templates for adapting the at least one payload; adapting the at least one payload using the one or more templates to generate at least one adapted payload formulated as a translation request; generating a second set of training data based on the at least one adapted payload; and training the machine-learning translation system using the second set of training data.