Patent · US Active

Domain adaptation in speech recognition via teacher-student learning

US10885900B2 · kind B2 · utility

5Cited by
24References
20Claims
0Family size

Assignee

Inventors

Key dates

Filing dateAug 11, 2017
Grant dateJan 5, 2021
Priority date
Expiry dateAug 11, 2037

Classification

  • Technology area (CPC G)Physics
  • CPC primaryG06N5/01
  • WIPO fieldComputer technology
  • WIPO sectorElectrical engineering

Abstract

Improvements in speech recognition in a new domain are provided via the student/teacher training of models for different speech domains. A student model for a new domain is created based on the teacher model trained in an existing domain. The student model is trained in parallel to the operation of the teacher model, with inputs in the new and existing domains respectfully, to develop a neural network that is adapted to recognize speech in the new domain. The data in the new domain may exclude transcription labels but rather are parallelized with the data analyzed in the existing domain analyzed by the teacher model. The outputs from the teacher model are compared with the outputs of the student model and the differences are used to adjust the parameters of the student model to better recognize speech in the second domain.

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