Google Inc.

Yeming Fang

Pedro Jose Moreno Mengibar

Ignacio Lopez Moreno

Quan Wang

Jin Shi

Jason William Pelecanos

Gang Feng

Fang Chu

A method of generating an accurate speaker representation for an audio sample includes receiving a first audio sample from a first speaker and a second audio sample from a second speaker. The method includes dividing a respective audio sample into a plurality of audio slices. The method also includes, based on the plurality of slices, generating a set of candidate acoustic embeddings where each candidate acoustic embedding includes a vector representation of acoustic features. The method further includes removing a subset of the candidate acoustic embeddings from the set of candidate acoustic embeddings. The method additionally includes generating an aggregate acoustic embedding from the remaining candidate acoustic embeddings in the set of candidate acoustic embeddings after removing the subset of the candidate acoustic embeddings.

Speaker identification accuracy

Growing community of inventors

Santa Clara, CA, United States of America

Yeming Fang