公开(公告)号：US20190222698A1

公开(公告)日：2019-07-18

申请号：US16333188

申请日：2016-09-21

Applicant: MOTOROLA SOLUTIONS, INC.

Inventor： Marta Tatiana MUSIK ,  Grzegorz KAPLITA ,  Wojciech T. WOJCIK

IPC: H04M3/56 ,  H04W4/10 ,  G10L15/08 ,  G06F16/68 ,  G06F16/638

Abstract: A method and system for optimizing voice recognition and information searching. The method includes determining context data associated with a particular talkgroup (140) that includes a plurality of communications devices (120) and creating a list of talkgroup-specific keywords associated with the context data, the list of talkgroup-specific keywords including a first characteristic for each talkgroup-specific keyword. The method also includes receiving, from a first communications device (120A) of the plurality of communications devices (120), audio data associated with a user of the first communications device (120A) and processing the audio data to generate an initial output term. The method further includes determining a second characteristic of the initial output term and determining whether the first characteristic of a talkgroup-specific keyword from the list of talkgroup-specific keywords matches the second characteristic of the initial output term. The method also includes outputting the keyword when the first characteristic matches the second characteristic.