公开(公告)号：US20200349921A1

公开(公告)日：2020-11-05

申请号：US16758564

申请日：2018-10-26

Applicant: Google LLC

Inventor： Aren Jansen ,  Manoj Plakal ,  Richard Channing Moore ,  Shawn Hershey ,  Ratheet Pandya ,  Ryan Rifkin ,  Jiayang Liu ,  Daniel Ellis

IPC: G10L15/06 ,  G10L25/18 ,  G10L15/02 ,  G10L25/51 ,  G06N3/04 ,  G06N3/08

Abstract: Methods are provided for generating training triplets that can be used to train multidimensional embeddings to represent the semantic content of non-speech sounds present in a corpus of audio recordings. These training triplets can be used with a triplet loss function to train the multidimensional embeddings such that the embeddings can be used to cluster the contents of a corpus of audio recordings, to facilitate a query-by-example lookup from the corpus, to allow a small number of manually-labeled audio recordings to be generalized, or to facilitate some other audio classification task. The triplet sampling methods may be used individually or collectively, and each represent a respective heuristic about the semantic structure of audio recordings.

公开(公告)号：US11335328B2

公开(公告)日：2022-05-17

申请号：US16758564

申请日：2018-10-26

Applicant: Google LLC

Inventor： Aren Jansen ,  Manoj Plakal ,  Richard Channing Moore ,  Shawn Hershey ,  Ratheet Pandya ,  Ryan Rifkin ,  Jiayang Liu ,  Daniel Ellis

IPC: G10L15/06 ,  G10L15/16 ,  G10L15/02 ,  G10L25/30 ,  G06N3/04 ,  G06N3/08 ,  G10L25/18 ,  G10L25/51

Abstract: Methods are provided for generating training triplets that can be used to train multidimensional embeddings to represent the semantic content of non-speech sounds present in a corpus of audio recordings. These training triplets can be used with a triplet loss function to train the multidimensional embeddings such that the embeddings can be used to cluster the contents of a corpus of audio recordings, to facilitate a query-by-example lookup from the corpus, to allow a small number of manually-labeled audio recordings to be generalized, or to facilitate some other audio classification task. The triplet sampling methods may be used individually or collectively, and each represent a respective heuristic about the semantic structure of audio recordings.