公开(公告)号：US11948559B2

公开(公告)日：2024-04-02

申请号：US17700378

申请日：2022-03-21

Applicant: QUALCOMM Incorporated

Inventor： Yang Yang ,  Anusha Lalitha ,  Jin Won Lee ,  Christopher Lott

IPC: G10L15/187 ,  G06F3/16 ,  G10L15/02 ,  G10L15/06 ,  G10L15/07 ,  G10L15/19 ,  G10L15/22

CPC classification number: G10L15/187 ,  G06F3/167 ,  G10L15/02 ,  G10L15/063 ,  G10L15/07 ,  G10L15/19 ,  G10L15/22

Abstract: Various embodiments include methods and devices for implementing automatic grammar augmentation for improving voice command recognition accuracy in systems with a small footprint acoustic model. Alternative expressions that may capture acoustic model decoding variations may be added to a grammar set. An acoustic model-specific statistical pronunciation dictionary may be derived by running the acoustic model through a large general speech dataset and constructing a command-specific candidate set containing potential grammar expressions. Greedy based and cross-entropy-method (CEM) based algorithms may be utilized to search the candidate set for augmentations with improved recognition accuracy.

公开(公告)号：US11586417B2

公开(公告)日：2023-02-21

申请号：US16147297

申请日：2018-09-28

Applicant: QUALCOMM Incorporated

Inventor： Rexford Hill ,  Aaron Lamb ,  Michael Goldfarb ,  Amin Ansari ,  Christopher Lott

IPC: G06F7/544 ,  G06F5/06 ,  G06N3/063

Abstract: A method of exploiting activation sparsity in deep neural networks is described. The method includes retrieving an activation tensor and a weight tensor where the activation tensor is a sparse activation tensor. The method also includes generating a compressed activation tensor comprising non-zero activations of the activation tensor, where the compressed activation tensor has fewer columns than the activation tensor. The method further includes processing the compressed activation tensor and the weight tensor to generate an output tensor.

公开(公告)号：US11282512B2

公开(公告)日：2022-03-22

申请号：US16665177

申请日：2019-10-28

Applicant: QUALCOMM Incorporated

Inventor： Yang Yang ,  Anusha Lalitha ,  Jin Won Lee ,  Christopher Lott

IPC: G10L15/187 ,  G10L15/06 ,  G10L15/22 ,  G10L15/19 ,  G10L15/07 ,  G06F3/16 ,  G10L15/02

Abstract: Various embodiments include methods and devices for implementing automatic grammar augmentation for improving voice command recognition accuracy in systems with a small footprint acoustic model. Alternative expressions that may capture acoustic model decoding variations may be added to a grammar set. An acoustic model-specific statistical pronunciation dictionary may be derived by running the acoustic model through a large general speech dataset and constructing a command-specific candidate set containing potential grammar expressions. Greedy based and cross-entropy-method (CEM) based algorithms may be utilized to search the candidate set for augmentations with improved recognition accuracy.

公开(公告)号：US12229192B2

公开(公告)日：2025-02-18

申请号：US18538965

申请日：2023-12-13

Applicant: QUALCOMM Incorporated

Inventor： Christopher Lott ,  Mingu Lee ,  Wonseok Jeon ,  Roland Memisevic

IPC: G06F16/901 ,  G06F40/284

Abstract: Certain aspects of the present disclosure provide techniques and apparatus for generating a response to a query input in a generative artificial intelligence model. An example method generally includes receiving a plurality of sets of tokens generated based on an input prompt and a first generative artificial intelligence model, each set of tokens in the plurality of sets of tokens corresponding to a candidate response to the input prompt; selecting, using a second generative artificial intelligence model and recursive adjustment of a target distribution associated with the received plurality of sets of tokens, a set of tokens from the plurality of sets of tokens; and outputting the selected set of tokens as a response to the input prompt.

公开(公告)号：US12131130B2

公开(公告)日：2024-10-29

申请号：US18105159

申请日：2023-02-02

Applicant: QUALCOMM Incorporated

Inventor： Rexford Alan Hill ,  Aaron Douglass Lamb ,  Michael Goldfarb ,  Amin Ansari ,  Christopher Lott

IPC: G06F7/544 ,  G06F5/06 ,  G06N3/063

CPC classification number: G06F7/5443 ,  G06F5/06 ,  G06N3/063

Abstract: A method of exploiting activation sparsity in deep neural networks is described. The method includes retrieving an activation tensor and a weight tensor where the activation tensor is a sparse activation tensor. The method also includes generating a compressed activation tensor comprising non-zero activations of the activation tensor, where the compressed activation tensor has fewer columns than the activation tensor. The method further includes processing the compressed activation tensor and the weight tensor to generate an output tensor.

公开(公告)号：US10093021B2

公开(公告)日：2018-10-09

申请号：US15192719

申请日：2016-06-24

Applicant: QUALCOMM Incorporated

Inventor： Aliakbar Aghamohammadi ,  Serafin Diaz Spindola ,  Bardia Fallah Behabadi ,  Christopher Lott ,  Shayegan Omidshafiei ,  Kiran Somasundaram ,  Sarah Paige Gibson ,  Casimir Matthew Wierzynski ,  Saurav Agarwal ,  Gerhard Reitmayr

IPC: B25J9/16 ,  G05D1/02 ,  G01C21/20 ,  G01C21/32

Abstract: A method substantially simultaneously plans a path and maps an environment by a robot. The method determines a mean of an occupancy level for a location in a map. The method also includes determining a probability distribution function (PDF) of the occupancy level. The method further includes calculating a cost function based on the PDF. Finally, the method includes simultaneously planning the path and mapping the environment based on the cost function.