KNOWLEDGE TRANSFER FOR RUSSIAN CONVERSATIONAL TELEPHONE AUTOMATIC SPEECH RECOGNITION

KNOWLEDGE TRANSFER FOR RUSSIAN CONVERSATIONAL TELEPHONE AUTOMATIC SPEECH RECOGNITION

This paper describes the method of knowledge transfer between the ensemble of neural network acoustic models and student-network. This method is used to reduce computational costs and improve the quality of the speech recognition system. The experiments consider two variants of generation of class l...

Full description

Bibliographic Details
Main Authors: A. N. Romanenko, Y. N. Matveev, W. Minker
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:
knowledge transfer
smoothing coefficient
softmax
automatic speech recognition
ensemble of neural networks
student-network
conversational telephone speech
Online Access:http://ntv.ifmo.ru/file/article/17617.pdf

Internet

http://ntv.ifmo.ru/file/article/17617.pdf

Similar Items