Model learning method, model learning apparatus, and program
AssigneeNTT, Inc.
InventorsTakanori ASHIHARA, Takaaki FUKUTOMI
Life of this patent
Estimating the term…
Abstract
A complicated speech representation is realized by a student model having a model size smaller than that of a teacher model. A model learning method according to one aspect of the present disclosure includes: generating an acoustic feature amount sequence X from a speech digital signal A; generating a teacher model representation sequence Y from the speech digital signal A using a teacher model TM that is a trained model trained by self-supervised learning; and training a student model SM having a model size smaller than a model size of the teacher model TM model using the acoustic feature amount sequence X and the teacher model representation sequence Y.
Claims20
A model learning method comprising:
- generating an acoustic feature amount sequence from a speech digital signal;
- generating a teacher model representation sequence from the speech digital signal using a teacher model that is a trained model trained by self-supervised learning;
- and
- training a student model having a model size smaller than a model size of the teacher model using the acoustic feature amount sequence and the teacher model representation sequence.
A model learning device comprising:
- at least one processor;
- and
- memory storing instructions that, when executed by the at least one processor, causes the device to perform a set of operations, the set of operations comprising:
- generating an acoustic feature amount sequence from a speech digital signal;
- generating a teacher model representation sequence from the speech digital signal using a teacher model that is a trained model trained by self-supervised learning;
- and
- training a student model having a model size smaller than a model size of the teacher model using the acoustic feature amount sequence and the teacher model representation sequence.
A computer-readable non-transitory recording medium storing computer-executable program instructions that when executed by a processor cause a computer to execute a program generation method comprising:
- generating an acoustic feature amount sequence from a speech digital signal;
- generating a teacher model representation sequence from the speech digital signal using a teacher model that is a trained model trained by self-supervised learning;
- and
- training a student model having a model size smaller than a model size of the teacher model using the acoustic feature amount sequence and the teacher model representation sequence.
Dependencies are inferred from the claim text.