公开(公告)号：US12230245B2

公开(公告)日：2025-02-18

申请号：US17900310

申请日：2022-08-31

Applicant: Nvidia Corporation

Inventor： Evelina Bakhturina ,  Yang Zhang ,  Boris Ginsburg

IPC: G06F17/00 ,  G06F40/40 ,  G10L13/047 ,  G10L13/08

Abstract: Systems and methods provide for text normalization or inverse text normalization using a hybrid language system that combines rule-based processing with neural or learned processing. For example, a hybrid rule-based and neural approach identifies semiotic tokens within a textual input and generates a set of potential plain-text conversions of the semiotic tokens. The plain-text conversions are weighted and evaluated by a trained language model that rescores the plain-text conversion based on context to identify a highest scoring plain-text conversion for further processing within a language system pipeline.

公开(公告)号：US20250022457A1

公开(公告)日：2025-01-16

申请号：US18349716

申请日：2023-07-10

Applicant: NVIDIA Corporation

Inventor： Xianchao Wu ,  Scott Nunweiler ,  Yang Zhang

IPC: G10L15/065 ,  G10L15/16

Abstract: Disclosed are systems and techniques for training machine learning models. The techniques include generating, using a first automatic speech recognition (ASR) model, a first text output based on a vector representation of a first speech data and generating, using a second ASR model, a second text output, wherein the second ASR model adds noise to a vector representation of the first text output to obtain a noisy vector representation of the first text output and is trained to remove the noise from the noisy vector representation of the first text output. The techniques include calculating a first loss of the second ASR model based at least on a comparison between the second text output and the first text output and modifying learnable parameters of the second ASR model to improve an accuracy of the second ASR model.

公开(公告)号：US20240071366A1

公开(公告)日：2024-02-29

申请号：US17900310

申请日：2022-08-31

Applicant: Nvidia Corporation

Inventor： Evelina Bakhturina ,  Yang Zhang ,  Boris Ginsburg

IPC: G10L13/08 ,  G06F40/40 ,  G10L13/047

CPC classification number: G10L13/08 ,  G06F40/40 ,  G10L13/047 ,  G10L2013/083

Abstract: Systems and methods provide for text normalization or inverse text normalization using a hybrid language system that combines rule-based processing with neural or learned processing. For example, a hybrid rule-based and neural approach identifies semiotic tokens within a textual input and generates a set of potential plain-text conversions of the semiotic tokens. The plain-text conversions are weighted and evaluated by a trained language model that rescores the plain-text conversion based on context to identify a highest scoring plain-text conversion for further processing within a language system pipeline.

公开(公告)号：US20250140236A1

公开(公告)日：2025-05-01

申请号：US19005596

申请日：2024-12-30

Applicant: Nvidia Corporation

Inventor： Evelina Bakhturina ,  Yang Zhang ,  Boris Ginsburg

IPC: G10L13/08 ,  G06F40/40 ,  G10L13/047

Abstract: Systems and methods provide for text normalization or inverse text normalization using a hybrid language system that combines rule-based processing with neural or learned processing. For example, a hybrid rule-based and neural approach identifies semiotic tokens within a textual input and generates a set of potential plain-text conversions of the semiotic tokens. The plain-text conversions are weighted and evaluated by a trained language model that rescores the plain-text conversion based on context to identify a highest scoring plain-text conversion for further processing within a language system pipeline.