Streaming action execution based on partial hypotheses

By using partial speech recognition hypotheses to execute sub-actions during user utterances, the method addresses latency issues in digital assistant interfaces, improving responsiveness and reliability on mobile devices.

JP7597935B2Active Publication Date: 2024-12-10GOOGLE LLC
7 Cites -1 Cited by

Patent Information

Application Number
JP2023534714
Authority / Receiving Office
JP · JP
Patent Type
Patents
Current Assignee / Owner
Priority Date
2020-12-08
Filing Date
2021-11-16
Publication Date
2024-12-10
Estimated Expiration
2041-11-16
Patent Text Reader

Abstract

A method (300) for streaming action performance receives audio data (14) corresponding to an utterance (20), the utterance including a query (22) for performing an action (24), the query (22) requiring execution of a sequence of sub-actions (26) to perform the action. While receiving the audio data, but before receiving an end-of-speech condition (214), the method processes the audio data to generate intermediate automatic speech recognition (ASR) results (212), performs partial query interpretation on the intermediate ASR results to determine whether the intermediate ASR results identify an application type needed to perform the action, and, when the intermediate ASR results identify the particular application type, performs a first sub-action in the sequence of sub-actions by launching a first application (118) for execution on the user device, the first application being associated with the particular application type. The method then performs execution of the action.
Need to check novelty before this filing date? Find Prior Art

Citation Information

Patent Citations

  • Application integration with digital assistant

    JP2018113035A

  • Completing headless tasks within a digital personal assistant

    JP2018511095A

  • Initiating actions based on partial hotwords

    US20170193998A1

  • Voice recognition system and construction method thereof

    US20180190292A1

  • Method for operating speech recognition service and electronic device for supporting the same

    US20190066674A1