公开(公告)号：WO2022246365A1

公开(公告)日：2022-11-24

申请号：PCT/US2022/072139

申请日：2022-05-05

Applicant: GOOGLE LLC

Inventor： MORENO, Ignacio Lopez ,  WANG, Quan ,  PELECANOS, Jason ,  HUANG, Yiling ,  SAGLAM, Mert

IPC: G10L17/18

Abstract: A speaker verification method (400) includes receiving audio data (120) corresponding to an utterance (119), processing the audio data to generate an evaluation attentive d-vector (200E) representing voice characteristics of the utterance, the evaluation ad-vector includes ne style classes (202) each including a respective value vector (220) concatenated with a corresponding routing vector (210). The method also includes generating using a self-attention mechanism (160), at least one multi-condition attention score (165) that indicates a likelihood that the evaluation ad-vector matches a respective reference ad-vector (200R) associated with a respective user (10). The method also includes identifying the speaker of the utterance as the respective user associated with the respective reference ad-vector based on the multi-condition attention score.