Title:
SPEECH RECOGNITION MODEL TRAINING DEVICE, SPEECH RECOGNITION MODEL TRAINING METHOD, AND PROGRAM
Document Type and Number:
WIPO Patent Application WO/2023/243083
Kind Code:
A1
Abstract:
A speech recognition model training device 1 comprises: a first speech conversion unit 11 that converts an auxiliary feature quantity XA into an auxiliary intermediate feature quantity HA using a first multilayer neural network; a second speech conversion unit 12 that receives, as inputs, and converts the auxiliary intermediate feature quantity HA and a mixed sound feature quantity XM into a target speaker intermediate feature quantity HS using a second multilayer neural network; a symbol conversion unit 13 that converts a symbol feature quantity c into an intermediate character feature quantity C using a third multilayer neural network; an estimation unit 14 that receives, as inputs, the target speaker intermediate feature quantity HS and the intermediate character feature quantity C and calculates an output probability distribution Y using a neural network; a loss calculation unit 15 that receive, as inputs, a correct answer symbol CT and the output probability distribution Y, and calculates a loss LRNN-T; and an updating unit 16 that updates the model parameters of the first speech conversion unit 11, the second speech conversion unit 12, the symbol conversion unit 13, and the estimation unit 14 using the loss LRNN-T.
Inventors:
MORIYA TAKAFUMI (JP)
SATO HIROSHI (JP)
DELCROIX MARC (JP)
OCHIAI TSUBASA (JP)
SATO HIROSHI (JP)
DELCROIX MARC (JP)
OCHIAI TSUBASA (JP)
Application Number:
PCT/JP2022/024344
Publication Date:
December 21, 2023
Filing Date:
June 17, 2022
Export Citation:
Assignee:
NIPPON TELEGRAPH & TELEPHONE (JP)
International Classes:
G10L15/16; G10L17/18
Foreign References:
| JP2019528476A | 2019-10-10 |
Attorney, Agent or Firm:
NAKAO, Naoki et al. (JP)
Download PDF: