Patents by Inventor Yeming Fang

Yeming Fang has filed for patents to protect the following inventions. This listing includes patent applications that are pending as well as patents that have already been granted by the United States Patent and Trademark Office (USPTO).

  • Publication number: 20230015169
    Abstract: 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.
    Type: Application
    Filed: September 19, 2022
    Publication date: January 19, 2023
    Applicant: Google LLC
    Inventors: Yeming Fang, Quan Wang, Pedro Jose Moreno Mengibar, Ignacio Lopez Moreno, Gang Feng, Fang Chu, Jin Shi, Jason William Pelecanos
  • Patent number: 11468900
    Abstract: 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.
    Type: Grant
    Filed: October 15, 2020
    Date of Patent: October 11, 2022
    Assignee: Google LLC
    Inventors: Yeming Fang, Quan Wang, Pedro Jose Moreno Mengibar, Ignacio Lopez Moreno, Gang Feng, Fang Chu, Jin Shi, Jason William Pelecanos
  • Publication number: 20220122612
    Abstract: 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.
    Type: Application
    Filed: October 15, 2020
    Publication date: April 21, 2022
    Applicant: Google LLC
    Inventors: Yeming Fang, Quan Wang, Pedro Jose Moreno Mengibar, Ignacio Lopez Moreno, Gang Feng, Fang Chu, Jin Shi, Jason William Pelecanos
  • Publication number: 20190005562
    Abstract: A server receives a request for a service from a first user that defines a location for the service and a category of the service. A first stage of matching is performed that includes determining second users that match the location and category. A second stage of matching is performed that includes performing for each second user: computing a first value that quantifies an attractiveness of the request to that second user, computing a second value that quantifies a likelihood of the first user selecting that second user to fulfill the request, and computing a third value based at least in part on the computed first and second values. A request for the service is transmitted to at least some of the second users whose computed third value exceeds a first threshold value.
    Type: Application
    Filed: March 14, 2018
    Publication date: January 3, 2019
    Inventors: Muxing Chen, Jeffrey Lock, Xin Liu, Benjamin Robert Anderson, Zhenyu Liu, Guqian Du, Chris Pak, Harsh Pankaj Panchal, Nick Jones, Shuai Ding, Xiao Zhang, Yeming Fang