公开(公告)号：US20240203399A1

公开(公告)日：2024-06-20

申请号：US18065692

申请日：2022-12-14

Applicant: Google LLC

Inventor： Adam Michael Stooke ,  Khe Chai Sim ,  Mason Vijay Chua

IPC: G10L15/06 ,  G10L15/16 ,  G10L15/183

CPC classification number: G10L15/063 ,  G10L15/16 ,  G10L15/183

Abstract: A method includes obtaining a training text sample, the training text sample not paired with corresponding audio data, and generating a sequence of pseudo-random encoder variables. The method also includes processing, using a decoder of a sequence transduction model, the sequence of pseudo-random encoder variables to predict a probability distribution over possible output labels. The method further includes determining a loss based metric based on the training text sample and the predicted probability distribution over possible output labels, and training the decoder based on the loss metric.