Analysis of voice imitation by professional/non-professional impersonators based on Kullback–Leibler divergence between acoustic models

2016 ◽  
Vol 140 (4) ◽  
pp. 3115-3115 ◽  
Author(s):  
Koji Iwano ◽  
Takuto Horihata
Keyword(s):  
Acoustic Models ◽  
Leibler Divergence ◽  
Voice Imitation

Large-sample confidence intervals of information-theoretic measures in linguistics

2020 ◽  
Vol 6 (1) ◽  
pp. 19-54
Author(s):  
Ryan Ka Yau Lai ◽  
Youngah Do
Keyword(s):  
Maximum Likelihood ◽  
Corpus Linguistics ◽  
Delta Method ◽  
Confidence Bounds ◽  
Likelihood Estimator ◽  
Information Theoretic ◽  
Leibler Divergence ◽  
Information Theoretic Measures ◽  
Data Points ◽  
Measure Of Uncertainty

This article explores a method of creating confidence bounds for information-theoretic measures in linguistics, such as entropy, Kullback-Leibler Divergence (KLD), and mutual information. We show that a useful measure of uncertainty can be derived from simple statistical principles, namely the asymptotic distribution of the maximum likelihood estimator (MLE) and the delta method. Three case studies from phonology and corpus linguistics are used to demonstrate how to apply it and examine its robustness against common violations of its assumptions in linguistics, such as insufficient sample size and non-independence of data points.

Domain Adaptation of CNN Based Acoustic Models Under Limited Resource Settings

2016 ◽  
Author(s):  
Masayuki Suzuki ◽  
Ryuki Tachibana ◽  
Samuel Thomas ◽  
Bhuvana Ramabhadran ◽  
George Saon
Keyword(s):  
Domain Adaptation ◽  
Limited Resource ◽  
Acoustic Models

Ensembles of Multi-Scale VGG Acoustic Models

2017 ◽  
Author(s):  
Michael Heck ◽  
Masayuki Suzuki ◽  
Takashi Fukuda ◽  
Gakuto Kurata ◽  
Satoshi Nakamura
Keyword(s):  
Acoustic Models ◽  
Multi Scale
Sign in / Sign up

Export Citation Format

Share Document