Qualcomm Incorporated

Simyung Chang

Byeonggeun Kim

Juntae Lee

Seunghan Yang

Hyunsin Park

Jaewon Choi

Inseop Chung

Fatih Murat Porikli

Kyu Woong Hwang

John Jiin Yang

Joo Seong Jeong

Yash Sanjay Bhalgat

Hyoungwoo Park

Jangho Kim

Kyuhong Shim

Sungha Choi

Various embodiments include systems and methods for continuous speech monitoring artificial intelligence solutions. A low-power always-on listening module (LPALM) may maintain continuous auditory awareness or alertness without consuming an excessive amount of the processing, memory, or battery resources of the user computing system or device. As such, the LPALM may operate on the computing device for an extended period of time without depleting the device's battery resources, rendering the user device non-responsive, or otherwise having a negative or user-perceivable impact on the performance, functionality, or power consumption characteristics of the user device.

Low power always-on listening artificial intelligence (AI) system

A method for generating a personalized model includes receiving one or more personal data samples from a user. A prototype of a personal identity is generated based on the personal data samples. The prototype of the personal identity is trained to reflect personal characteristics of the user. A network graph is generated based on the prototype of the personal identity. One or more channels of a global network are pruned based on the network graph to produce the personalized model.

Personalized neural network pruning

Systems and techniques are provided for processing audio data. For example, a dummy prototypical network may be used to perform few-shot open-set keyword spotting (FSOS-KWS). A process can include determining one or more prototype representations based on a plurality of support samples associated with one or more classes. Each prototype representation may be associated with one of the class(es). A dummy prototype representation can be determined in a same learned metric space as the prototype representations. One or more distance metrics can be determined for each query sample of one or more query samples. The distance metrics may be based on the prototype representations and the dummy prototype representation. Each query sample can be classified based on the distance metrics. Each query sample may be classified into one of the class(es) associated with the prototype representations or into an open-set class associated with the dummy prototype representation.

Dummy prototypical networks for few-shot open-set keyword spotting

Systems and techniques are provided for processing audio data. For example, the systems and techniques can be used for personalized keyword spotting through multi-task learning (PK-MTL). A process can include obtaining an audio sample, generating a representation of a keyword based on the audio sample, and generating a representation of a speaker based on the audio sample. The speaker can be associated with the keyword. A first similarity score can be determined based on a reference representation and one or more of the representation of the keyword and a representation of the speaker. The reference representation can be associated with one or more of the keyword and the speaker. A keyword spotting (KWS) output can be generated based on analyzing the first similarity score against at least a first threshold, wherein the KWS output accepts or rejects the audio sample as including a target keyword.

Multi-task learning for personalized keyword spotting

Techniques and apparatus for training a neural network to classify audio into one of a plurality of categories and using such a trained neural network. An example method generally includes receiving a data set including a plurality of audio samples. A relaxed feature-normalized data set is generated by normalizing each audio sample of the plurality of audio samples. A neural network is trained to classify audio into one of a plurality of categories based on the relaxed feature-normalized data set, and the trained neural network is deployed.

Relaxed instance frequency normalization for neural-network-based audio processing

Systems and techniques are provided for processing one or more data samples. For example, a neural network classifier can be trained to perform few-shot open-set recognition (FSOSR) based on a task-agnostic open-set prototype. A process can include determining one or more prototype representations for each class included in a plurality of support samples. A task-agnostic open-set prototype representation can be determined, in a same learned metric space as the one or more prototype representations. One or more distance metrics can be determined for each query sample of one or more query samples, based on the one or more prototype representations and the task-agnostic open-set prototype representation. Based on the one or more distance metrics, each query sample can be classified into one of classes associated with the one or more prototype representations or an open-set class associated with the task-agnostic open-set prototype representation.

Task agnostic open-set prototypes for few-shot open-set recognition

Certain aspects of the present disclosure provide a method, including: processing input data with a feature extraction stage of a machine learning model to generate a feature map; applying an attention map to the feature map to generate an augmented feature map; processing the augmented feature map with a refinement stage of the machine learning model to generate a refined feature map; processing the refined feature map with a first regression stage of the machine learning model to generate multi-dimensional task output data; and processing the refined feature data with an attention stage of the machine learning model to generate an updated attention map.

Efficient pose estimation through iterative refinement

Imaging systems and techniques are described. An imaging system receives image data representing at least a portion (e.g., a face) of a first user as captured by a first image sensor. The imaging system identifies that a gaze of the first user as represented in the image data is directed toward a displayed representation of at least a portion (e.g., a face) of a second user. The imaging system identifies an arrangement of representations of users for output. The imaging system generates modified image data based on the gaze and the arrangement at least in part by modifying the image data to modify at least the portion of the first user in the image data to be visually directed toward a direction corresponding to the second user based on the gaze and the arrangement. The imaging system outputs the modified image data arranged according to the arrangement.

Growing community of inventors

Suwon, South Korea

Simyung Chang