公开(公告)号：US20240403539A1

公开(公告)日：2024-12-05

申请号：US18764129

申请日：2024-07-03

Applicant: Microsoft Technology Licensing, LLC

Inventor： Wei LIU ,  Padma VARADHARAJAN ,  Piyush BEHRE ,  Nicholas KIBRE ,  Edward C. LIN ,  Shuangyu CHANG ,  Che ZHAO ,  Khuram SHAHID ,  Heiko Willy RAHMEL

IPC: G06F40/151 ,  G06F40/117 ,  G06F40/166 ,  G06F40/284

Abstract: Solutions for custom display post processing (DPP) in speech recognition (SR) use a customized multi-stage DPP pipeline that transforms a stream of SR tokens from lexical form to display form. A first transformation stage of the DPP pipeline receives the stream of tokens, in turn, by an upstream filter, a base model stage, and a downstream filter, and transforms a first aspect of the stream of tokens (e.g., disfluency, inverse text normalization (ITN), capitalization, etc.) from lexical form into display form. The upstream filter and/or the downstream filter alter the stream of tokens to change the default behavior of the DPP pipeline into custom behavior. Additional transformation stages of the DPP pipeline perform further transforms, allowing for outputting final text in a display format that is customized for a specific user. This permits each user to efficiently leverage a common baseline DPP pipeline to produce a custom output.

公开(公告)号：US20230351098A1

公开(公告)日：2023-11-02

申请号：US17815211

申请日：2022-07-26

Applicant: Microsoft Technology Licensing, LLC

Inventor： Wei LIU ,  Padma VARADHARAJAN ,  Piyush BEHRE ,  Nicholas KIBRE ,  Edward C. LIN ,  Shuangyu CHANG ,  Che ZHAO ,  Khuram SHAHID ,  Heiko Willy RAHMEL

IPC: G06F40/151 ,  G06F40/117 ,  G06F40/166 ,  G06F40/284

CPC classification number: G06F40/151 ,  G06F40/117 ,  G06F40/166 ,  G06F40/284

Abstract: Solutions for custom display post processing (DPP) in speech recognition (SR) use a customized multi-stage DPP pipeline that transforms a stream of SR tokens from lexical form to display form. A first transformation stage of the DPP pipeline receives the stream of tokens, in turn, by an upstream filter, a base model stage, and a downstream filter, and transforms a first aspect of the stream of tokens (e.g., disfluency, inverse text normalization (ITN), capitalization, etc.) from lexical form into display form. The upstream filter and/or the downstream filter alter the stream of tokens to change the default behavior of the DPP pipeline into custom behavior. Additional transformation stages of the DPP pipeline perform further transforms, allowing for outputting final text in a display format that is customized for a specific user. This permits each user to efficiently leverage a common baseline DPP pipeline to produce a custom output.

公开(公告)号：US20230401392A1

公开(公告)日：2023-12-14

申请号：US17836390

申请日：2022-06-09

Applicant: Microsoft Technology Licensing, LLC

Inventor： Kshitiz KUMAR ,  Jian WU ,  Bo REN ,  Tianyu WU ,  Fahimeh BAHMANINEZHAD ,  Edward C. LIN ,  Xiaoyang CHEN ,  Changliang LIU

IPC: G06F40/58 ,  G10L15/00 ,  G10L15/16 ,  G10L15/06

CPC classification number: G06F40/58 ,  G10L15/005 ,  G10L15/16 ,  G10L15/063

Abstract: A data processing system is implemented for receiving speech data for a plurality of languages, and determining letters from the speech data. The data processing system also implements normalizing the speech data by applying linguistic based rules for Latin-based languages on the determined letters, building a computer model using the normalized speech data, fine-tuning the computer model using additional speech data, and recognizing words in a target language using the fine-tuned computer model.

公开(公告)号：US20230186919A1

公开(公告)日：2023-06-15

申请号：US18108316

申请日：2023-02-10

Applicant: Microsoft Technology Licensing, LLC

Inventor： Guoli YE ,  Yan HUANG ,  Wenning WEI ,  Lei HE ,  Eva SHARMA ,  Jian WU ,  Yao TIAN ,  Edward C. LIN ,  Yifan GONG ,  Rui ZHAO ,  Jinyu LI ,  William Maxwell GALE

IPC: G10L15/26 ,  G10L13/08 ,  G10L15/06 ,  G10L15/16

CPC classification number: G10L15/26 ,  G10L13/08 ,  G10L15/063 ,  G10L15/16

Abstract: Systems, methods, and devices are provided for generating and using text-to-speech (TTS) data for improved speech recognition models. A main model is trained with keyword independent baseline training data. In some instances, acoustic and language model sub-components of the main model are modified with new TTS training data. In some instances, the new TTS training is obtained from a multi-speaker neural TTS system for a keyword that is underrepresented in the baseline training data. In some instances, the new TTS training data is used for pronunciation learning and normalization of keyword dependent confidence scores in keyword spotting (KWS) applications. In some instances, the new TTS training data is used for rapid speaker adaptation in speech recognition models.