FEATURE COMBINATION FOR THE TASK OF NEURAL NETWORK ACOUSTIC MODEL LEARNING

FEATURE COMBINATION FOR THE TASK OF NEURAL NETWORK ACOUSTIC MODEL LEARNING

A method of feature combination for the problem of neural network acoustic models training is proposed aimed at the quality improvement of speech recognition. Unlike the feeding of a concatenated vector of features of a different nature to the neural network input, the proposed method uses a delayed...

Full description

Bibliographic Details
Main Author: A. N. Romanenko
Format: Article
Language:English
Published: Saint Petersburg National Research University of Information Technologies, Mechanics and Optics (ITMO University) 2018-03-01
Series:Naučno-tehničeskij Vestnik Informacionnyh Tehnologij, Mehaniki i Optiki
Subjects:
feature combination
neural network acoustic models
speech recognition
Online Access:http://ntv.ifmo.ru/file/article/17646.pdf

Internet

http://ntv.ifmo.ru/file/article/17646.pdf

Similar Items