公开(公告)号：US20240203406A1

公开(公告)日：2024-06-20

申请号：US18065685

申请日：2022-12-14

Applicant: Google LLC

Inventor： Soheil Khorram ,  Anshuman Tripathi ,  Kim Jaeyoung ,  Han Lu ,  Qian Zhang ,  Hasim Sak

IPC: G10L15/183 ,  G10L15/06 ,  G10L15/22

CPC classification number: G10L15/183 ,  G10L15/063 ,  G10L15/22

Abstract: A method includes receiving a sequence of acoustic frames extracted from unlabeled audio samples that correspond to spoken utterances not paired with any corresponding transcriptions. The method also includes generating, using a supervised audio encoder, a target higher order feature representation for a corresponding acoustic frame. The method also includes augmenting the sequence of acoustic frames and generating, as output form an unsupervised audio encoder, a predicted higher order feature representation for a corresponding augmented acoustic frame in the sequence of augmented acoustic frames. The method also includes determining an unsupervised loss term based on the target higher order feature representation and the predicted higher order feature representation and updating parameters of the speech recognition model based on the unsupervised loss term.