SPEAKER-DEPENDENT FEATURES FOR SPONTANEOUS SPEECH RECOGNITION

SPEAKER-DEPENDENT FEATURES FOR SPONTANEOUS SPEECH RECOGNITION

This paper presents the results of the study on improving robustness to the acoustic variability of the speech signal for spontaneous speech recognition system. The method is proposed to constructing high-level bottleneck features using deep neural network adapted to a speaker and to acoustic enviro...

Full description

Bibliographic Details
Main Author: I. P. Medennikov
Format: Article
Language:English
Published: Saint Petersburg National Research University of Information Technologies, Mechanics and Optics (ITMO University) 2016-01-01
Series:Naučno-tehničeskij Vestnik Informacionnyh Tehnologij, Mehaniki i Optiki
Subjects:
automatic speech recognition
speaker adaptation
i-vectors
bottleneck features from deep neural network
Online Access:http://ntv.ifmo.ru/file/article/14589.pdf

Internet

http://ntv.ifmo.ru/file/article/14589.pdf

Similar Items