Patent · US Active

Tied and reduced RNN-T

US11727920B2 · kind B2 · utility

1Cited by
8References
24Claims
0Family size

Assignee

Inventors

Key dates

Filing dateMay 26, 2021
Grant dateAug 15, 2023
Priority date
Expiry dateOct 14, 2041

Classification

  • Technology area (CPC G)Physics
  • CPC primaryG10L15/083
  • WIPO fieldComputer technology
  • WIPO sectorElectrical engineering

Abstract

A RNN-T model includes a prediction network configured to, at each of a plurality of times steps subsequent to an initial time step, receive a sequence of non-blank symbols. For each non-blank symbol the prediction network is also configured to generate, using a shared embedding matrix, an embedding of the corresponding non-blank symbol, assign a respective position vector to the corresponding non-blank symbol, and weight the embedding proportional to a similarity between the embedding and the respective position vector. The prediction network is also configured to generate a single embedding vector at the corresponding time step. The RNN-T model also includes a joint network configured to, at each of the plurality of time steps subsequent to the initial time step, receive the single embedding vector generated as output from the prediction network at the corresponding time step and generate a probability distribution over possible speech recognition hypotheses.

Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.