METHOD AND DEVICE FOR ACOUSTIC LANGUAGE MODEL TRAINING
First Claim
1. A method of training an acoustic language model, comprising:
- at a device having one or more processors and memory;
conducting word segmentation for training samples in a training corpus using an initial language model containing no word class labels, to obtain initial word segmentation data containing no word class labels;
performing word class replacement for the initial word segmentation data containing no word class labels, to obtain first word segmentation data containing word class labels;
using the first word segmentation data containing word class labels to train a first language model containing word class labels;
using the first language model containing word class labels to conduct word segmentation for the training samples in the training corpus, to obtain second word segmentation data containing word class labels; and
in accordance with the second word segmentation data meeting one or more predetermined criteria, using the second word segmentation data containing word class labels to train the acoustic language model.
1 Assignment
0 Petitions
Accused Products
Abstract
A method and a device for training an acoustic language model, include: conducting word segmentation for training samples in a training corpus using an initial language model containing no word class labels, to obtain initial word segmentation data containing no word class labels; performing word class replacement for the initial word segmentation data containing no word class labels, to obtain first word segmentation data containing word class labels; using the first word segmentation data containing word class labels to train a first language model containing word class labels; using the first language model containing word class labels to conduct word segmentation for the training samples in the training corpus, to obtain second word segmentation data containing word class labels; and in accordance with the second word segmentation data meeting one or more predetermined criteria, using the second word segmentation data containing word class labels to train the acoustic language model.
-
Citations
20 Claims
-
1. A method of training an acoustic language model, comprising:
at a device having one or more processors and memory; conducting word segmentation for training samples in a training corpus using an initial language model containing no word class labels, to obtain initial word segmentation data containing no word class labels; performing word class replacement for the initial word segmentation data containing no word class labels, to obtain first word segmentation data containing word class labels; using the first word segmentation data containing word class labels to train a first language model containing word class labels; using the first language model containing word class labels to conduct word segmentation for the training samples in the training corpus, to obtain second word segmentation data containing word class labels; and in accordance with the second word segmentation data meeting one or more predetermined criteria, using the second word segmentation data containing word class labels to train the acoustic language model. - View Dependent Claims (2, 3, 4, 5, 6, 7)
-
8. A system for training an acoustic language model, comprising:
-
one or more processors; and memory having instructions stored thereon, the instructions, when executed by the one or more processors, cause the processors to perform operations comprising; conducting word segmentation for training samples in a training corpus using an initial language model containing no word class labels, to obtain initial word segmentation data containing no word class labels; performing word class replacement for the initial word segmentation data containing no word class labels, to obtain first word segmentation data containing word class labels; using the first word segmentation data containing word class labels to train a first language model containing word class labels; using the first language model containing word class labels to conduct word segmentation for the training samples in the training corpus, to obtain second word segmentation data containing word class labels; and in accordance with the second word segmentation data meeting one or more predetermined criteria, using the second word segmentation data containing word class labels to train the acoustic language model. - View Dependent Claims (9, 10, 11, 12, 13, 14)
-
-
15. A non-transitory computer-readable medium for training an acoustic language model, having instructions stored thereon, the instructions, when executed by one or more processors, cause the processors to perform operations comprising:
-
conducting word segmentation for training samples in a training corpus using an initial language model containing no word class labels, to obtain initial word segmentation data containing no word class labels; performing word class replacement for the initial word segmentation data containing no word class labels, to obtain first word segmentation data containing word class labels; using the first word segmentation data containing word class labels to train a first language model containing word class labels; using the first language model containing word class labels to conduct word segmentation for the training samples in the training corpus, to obtain second word segmentation data containing word class labels; and in accordance with the second word segmentation data meeting one or more predetermined criteria, using the second word segmentation data containing word class labels to train the acoustic language model. - View Dependent Claims (16, 17, 18, 19, 20)
-
Specification