The application of hidden Markov models in speech recognition

M Gales, S Young - Foundations and Trends® in Signal …, 2008 - nowpublishers.com
The Application of Hidden Markov Models in Speech Recognition Page 1 The Application of
Hidden Markov Models in Speech Recognition Full text available at: http://dx.doi.org/10.1561/2000000004 …

Developments of Machine Learning Schemes for Dynamic Time‐Wrapping‐Based Speech Recognition

IJ Ding, CT Yen, YM Hsu - Mathematical Problems in …, 2013 - Wiley Online Library
This paper presents a machine learning scheme for dynamic time‐wrapping‐based (DTW)
speech recognition. Two categories of learning strategies, supervised and unsupervised …

An ensemble speaker and speaking environment modeling approach to robust speech recognition

Y Tsao, CH Lee - IEEE transactions on audio, speech, and …, 2009 - ieeexplore.ieee.org
We propose an ensemble speaker and speaking environment modeling (ESSEM) approach
to characterizing environments in order to enhance performance robustness of automatic …

Noise in HMM-based speech synthesis adaptation: Analysis, evaluation methods and experiments

R Karhila, U Remes, M Kurimo - IEEE Journal of Selected …, 2013 - ieeexplore.ieee.org
This work describes experiments on using noisy adaptation data to create personalized
voices with HMM-based speech synthesis. We investigate how environmental noise affects …

Robust speech recognition under noisy ambient conditions

KK Paliwal, K Yao - Human-centric interfaces for ambient intelligence, 2010 - Elsevier
Publisher Summary This chapter provides an overview of an automatic speech recognition
system and describes sources of speech variability that cause mismatch between training …

Robust several-speaker speech recognition with highly dependable online speaker adaptation and identification

PY Shih, PC Lin, JF Wang, YN Lin - Journal of network and computer …, 2011 - Elsevier
The currently adaptive mechanisms adapt a single acoustic model for a speaker in speaker-
independent speech recognition system. However, as more users use the same speech …

Factored MLLR adaptation

NS Kim, JS Sung, DH Hong - IEEE Signal Processing Letters, 2010 - ieeexplore.ieee.org
One of the most popular approaches to parameter adaptation in hidden Markov model
(HMM) based systems is the maximum likelihood linear regression (MLLR) technique. In this …

Maximum penalized likelihood kernel regression for fast adaptation

BKW Mak, TC Lai, IW Tsang… - IEEE transactions on …, 2009 - ieeexplore.ieee.org
This paper proposes a nonlinear generalization of the popular maximum-likelihood linear
regression (MLLR) adaptation algorithm using kernel methods. The proposed method …

Rapid speaker adaptation using clustered maximum-likelihood linear basis with sparse training data

Y Tang, R Rose - IEEE transactions on audio, speech, and …, 2008 - ieeexplore.ieee.org
Speaker space-based adaptation methods for automatic speech recognition have been
shown to provide significant performance improvements for tasks where only a few seconds …

[PDF][PDF] Factored MLLR adaptation for singing voice generation

JS Sung, DH Hong, SJ Kang, NS Kim - Twelfth Annual Conference …, 2011 - isca-archive.org
In our previous study, we proposed factored MLLR (FMLLR) where each MLLR parameter is
defined as a function of a control vector. We presented a method to train the FMLLR …