公开(公告)号：US11942091B2

公开(公告)日：2024-03-26

申请号：US17251465

申请日：2020-01-17

Applicant: Google LLC

Inventor： Benjamin Haynor ,  Petar Aleksic

IPC: G10L15/26 ,  G10L15/16 ,  G10L15/193 ,  G10L15/22 ,  G10L15/30

CPC classification number: G10L15/26 ,  G10L15/16 ,  G10L15/193 ,  G10L15/22 ,  G10L15/30

Abstract: Speech processing techniques are disclosed that enable determining a text representation of alphanumeric sequences in captured audio data. Various implementations include determining a contextual biasing finite state transducer (FST) based on contextual information corresponding to the captured audio data. Additional or alternative implementations include modifying probabilities of one or more candidate recognitions of the alphanumeric sequence using the contextual biasing FST, where the FST further comprises a grammar as well as a speller finite state transducer.

公开(公告)号：US20240233732A1

公开(公告)日：2024-07-11

申请号：US18615621

申请日：2024-03-25

Applicant: GOOGLE LLC

Inventor： Benjamin Haynor ,  Petar Aleksic

IPC: G10L15/26 ,  G10L15/16 ,  G10L15/193 ,  G10L15/22 ,  G10L15/30

CPC classification number: G10L15/26 ,  G10L15/16 ,  G10L15/193 ,  G10L15/22 ,  G10L15/30

Abstract: Speech processing techniques are disclosed that enable determining a text representation of alphanumeric sequences in captured audio data. Various implementations include determining a contextual biasing finite state transducer (FST) based on contextual information corresponding to the captured audio data. Additional or alternative implementations include modifying probabilities of one or more candidate recognitions of the alphanumeric sequence using the contextual biasing FST.

公开(公告)号：US12283278B2

公开(公告)日：2025-04-22

申请号：US18615621

申请日：2024-03-25

Applicant: GOOGLE LLC

Inventor： Benjamin Haynor ,  Petar Aleksic

IPC: G10L15/26 ,  G10L15/16 ,  G10L15/193 ,  G10L15/22 ,  G10L15/30

Abstract: Speech processing techniques are disclosed that enable determining a text representation of alphanumeric sequences in captured audio data. Various implementations include determining a contextual biasing finite state transducer (FST) based on contextual information corresponding to the captured audio data. Additional or alternative implementations include modifying probabilities of one or more candidate recognitions of the alphanumeric sequence using the contextual biasing FST.

公开(公告)号：US20220013126A1

公开(公告)日：2022-01-13

申请号：US17251465

申请日：2020-01-17

Applicant: Google LLC

Inventor： Benjamin Haynor ,  Petar Aleksic

IPC: G10L15/26 ,  G10L15/16 ,  G10L15/193

Abstract: Speech processing techniques are disclosed that enable determining a text representation of alphanumeric sequences in captured audio data. Various implementations include determining a contextual biasing finite state transducer (FST) based on contextual information corresponding to the captured audio data. Additional or alternative implementations include modifying probabilities of one