Adversarial teacher-student learning for unsupervised domain adaptation
US10643602B2 · kind B2 · utility
Assignee
Inventors
Key dates
| Filing date | Mar 16, 2018 |
| Grant date | May 5, 2020 |
| Priority date | — |
| Expiry date | Nov 2, 2038 |
Classification
- Technology area (CPC G)Physics
- CPC primaryG10L15/16
- WIPO fieldComputer technology
- WIPO sectorElectrical engineering
Abstract
Methods, systems, and computer programs are presented for training, with adversarial constraints, a student model for speech recognition based on a teacher model. One method includes operations for training a teacher model based on teacher speech data, initializing a student model with parameters obtained from the teacher model, and training the student model with adversarial teacher-student learning based on the teacher speech data and student speech data. Training the student model with adversarial teacher-student learning further includes minimizing a teacher-student loss that measures a divergence of outputs between the teacher model and the student model; minimizing a classifier condition loss with respect to parameters of a condition classifier; and maximizing the classifier condition loss with respect to parameters of a feature extractor. The classifier condition loss measures errors caused by acoustic condition classification. Further, speech is recognized with the trained student model.
Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.