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...
Saved in:
| Main Author: | |
|---|---|
| Format: | Artigo |
| Language: | Inglês |
| Published: |
ITMO University
2018-03-01
|
| Series: | Научно-технический вестник информационных технологий, механики и оптики |
| Subjects: | |
| Online Access: | http://ntv.ifmo.ru/file/article/17646.pdf |
| Tags: |
No Tags, Be the first to tag this record!
|