利索-全球专利检索

  1. 登录
  2. 注册

搜索结果

9 条记录 (耗时 0.014 秒)

    VOICE TO TEXT CONVERSION BASED ON THIRD-PARTY AGENT CONTENT
    1.
    发明公开
    VOICE TO TEXT CONVERSION BASED ON THIRD-PARTY AGENT CONTENT 审中-公开

    公开(公告)号：EP3926625A1

    公开(公告)日：2021-12-22

    申请号：EP21190701.9

    申请日：2017-09-21

    申请人： Google LLC

    发明人： JAMES, Barnaby ,  WANG, Bo ,  VEMURI, Sunil ,  SCHAIRER, David ,  KIRAZCI, Ulas ,  DOGRULTAN, Ertan ,  ALEKSIC, Petar

    IPC分类号： G10L15/22 ,  G10L15/26

    摘要： Implementations relate to dynamically, and in a context-sensitive manner, biasing voice to text conversion. In some implementations, the biasing of voice to text conversions is performed by a voice to text engine of a local agent, and the biasing is based at least in part on content provided to the local agent by a third-party (3P) agent that is in network communication with the local agent. In some of those implementations, the content includes contextual parameters that are provided by the 3P agent in combination with responsive content generated by the 3P agent during a dialog that: is between the 3P agent, and a user of a voice-enabled electronic device; and is facilitated by the local agent. The contextual parameters indicate potential feature(s) of further voice input that is to be provided in response to the responsive content generated by the 3P agent. Implementations described herein reduce the use of various computational resources that may otherwise be consumed by inaccurate representations of voice inputs (e.g., network traffic consumed by additional "turns" that may be necessary to correct inaccurate representations of voice input).

    VOICE TO TEXT CONVERSION BASED ON THIRD-PARTY AGENT CONTENT
    2.
    发明公开
    VOICE TO TEXT CONVERSION BASED ON THIRD-PARTY AGENT CONTENT 审中-实审

    公开(公告)号：EP4332959A3

    公开(公告)日：2024-05-15

    申请号：EP24150123.8

    申请日：2017-09-21

    申请人： Google LLC

    发明人： JAMES, Barnaby ,  WANG, Bo ,  VEMURI, Sunil ,  SCHAIRER, David ,  KIRAZCI, Ulas ,  DOGRULTAN, Ertan ,  ALEKSIC, Petar

    IPC分类号： G10L15/22 ,  G10L15/26

    CPC分类号： G10L15/22 ,  G10L15/26 ,  G10L2015/22820130101

    摘要： Implementations relate to dynamically, and in a context-sensitive manner, biasing voice to text conversion. In some implementations, the biasing of voice to text conversions is performed by a voice to text engine of a local agent, and the biasing is based at least in part on content provided to the local agent by a third-party (3P) agent that is in network communication with the local agent. In some of those implementations, the content includes contextual parameters that are provided by the 3P agent in combination with responsive content generated by the 3P agent during a dialog that: is between the 3P agent, and a user of a voice-enabled electronic device; and is facilitated by the local agent. The contextual parameters indicate potential feature(s) of further voice input that is to be provided in response to the responsive content generated by the 3P agent. Implementations described herein reduce the use of various computational resources that may otherwise be consumed by inaccurate representations of voice inputs (e.g., network traffic consumed by additional "turns" that may be necessary to correct inaccurate representations of voice input).

    VOICE TO TEXT CONVERSION BASED ON THIRD-PARTY AGENT CONTENT
    7.
    发明公开
    VOICE TO TEXT CONVERSION BASED ON THIRD-PARTY AGENT CONTENT 审中-公开

    公开(公告)号：EP4332959A2

    公开(公告)日：2024-03-06

    申请号：EP24150123.8

    申请日：2017-09-21

    申请人： Google LLC

    发明人： JAMES, Barnaby ,  WANG, Bo ,  VEMURI, Sunil ,  SCHAIRER, David ,  KIRAZCI, Ulas ,  DOGRULTAN, Ertan ,  ALEKSIC, Petar

    IPC分类号： G10L15/26

    摘要： Implementations relate to dynamically, and in a context-sensitive manner, biasing voice to text conversion. In some implementations, the biasing of voice to text conversions is performed by a voice to text engine of a local agent, and the biasing is based at least in part on content provided to the local agent by a third-party (3P) agent that is in network communication with the local agent. In some of those implementations, the content includes contextual parameters that are provided by the 3P agent in combination with responsive content generated by the 3P agent during a dialog that: is between the 3P agent, and a user of a voice-enabled electronic device; and is facilitated by the local agent. The contextual parameters indicate potential feature(s) of further voice input that is to be provided in response to the responsive content generated by the 3P agent. Implementations described herein reduce the use of various computational resources that may otherwise be consumed by inaccurate representations of voice inputs ( e.g., network traffic consumed by additional "turns" that may be necessary to correct inaccurate representations of voice input).