Skip to search form
Skip to main content
Skip to account menu
Semantic Scholar
Semantic Scholar's Logo
Search 210,223,234 papers from all fields of science
Search
Sign In
Create Free Account
FMLLR
Feature space Maximum Likelihood Linear Regression (fMLLR) is a widely used technique for speaker adaptation in HMM-based speech recognition.
Wikipedia
(opens in a new tab)
Create Alert
Alert
Related topics
Related topics
5 relations
Broader (2)
Automatic identification and data capture
Speech recognition
Feature scaling
Hidden Markov model
Kernel eigenvoice
Papers overview
Semantic Scholar uses AI to extract papers important to this topic.
2020
2020
Subspace Gaussian mixture based language modeling for large vocabulary continuous speech recognition
Ri Hyon Sun
,
Ri Jong Chol
Speech Communication
2020
Corpus ID: 212858411
2016
2016
Feature mapping using far-field microphones for distant speech recognition
Ivan Himawan
,
P. Motlícek
,
David Imseng
,
S. Sridharan
Speech Communication
2016
Corpus ID: 200541
2016
2016
Towards Robust Indonesian Speech Recognition with Spontaneous-Speech Adapted Acoustic Models
Devin Hoesen
,
C. H. Satriawan
,
D. Lestari
,
M. L. Khodra
Workshop on Spoken Language Technologies for…
2016
Corpus ID: 4957070
2016
2016
DNNs for Unsupervised Extraction of Pseudo FMLLR Features Without Explicit Adaptation Data
N. M. Joy
,
Murali Karthick Baskar
,
S. Umesh
,
B. Abraham
Interspeech
2016
Corpus ID: 34328314
In this paper, we propose the use of deep neural networks (DNN) as a regression model to estimate feature-space maximum…
Expand
Highly Cited
2016
Highly Cited
2016
Sequence summarizing neural network for speaker adaptation
Karel Veselý
,
Shinji Watanabe
,
Kateřina Žmolíková
,
M. Karafiát
,
L. Burget
,
J. Černocký
IEEE International Conference on Acoustics…
2016
Corpus ID: 11367026
In this paper, we propose a DNN adaptation technique, where the i-vector extractor is replaced by a Sequence Summarizing Neural…
Expand
2013
2013
Rapid speaker adaptation in latent speaker space with non-negative matrix factorization
Xueru Zhang
,
Kris Demuynck
,
H. V. hamme
Speech Communication
2013
Corpus ID: 27105749
Highly Cited
2013
Highly Cited
2013
Improvements to Deep Convolutional Neural Networks for LVCSR
Tara N. Sainath
,
Brian Kingsbury
,
+6 authors
B. Ramabhadran
IEEE Workshop on Automatic Speech Recognition and…
2013
Corpus ID: 4690220
Deep Convolutional Neural Networks (CNNs) are more powerful than Deep Neural Networks (DNN), as they are able to better reduce…
Expand
2012
2012
Initialization of adaptation by sufficient statistics using phonetic tree
Zbynek Zajíc
,
Lukás Machlica
,
Ludek Muller
IEEE 11th International Conference on Signal…
2012
Corpus ID: 12987560
In this work we deal with the problem of small amount of data when estimating a feature transformation for the speaker adaptation…
Expand
2009
2009
Refinement Approach for Adaptation Based on Combination of MAP and fMLLR
Zbynek Zajíc
,
Lukás Machlica
,
L. Müller
International Conference on Text, Speech and…
2009
Corpus ID: 12990695
This paper deals with a combination of basic adaptation techniques of Hidden Markov Model used in the speech recognition. The…
Expand
2008
2008
Quick fmllr for speaker adaptation in speech recognition
Balakrishnan Varadarajan
,
Daniel Povey
,
Selina M. Chu
IEEE International Conference on Acoustics…
2008
Corpus ID: 14587630
Feature space maximum likelihood linear regression (fMLLR) is a widely used technique for speaker adaptation in HMM-based speech…
Expand
By clicking accept or continuing to use the site, you agree to the terms outlined in our
Privacy Policy
(opens in a new tab)
,
Terms of Service
(opens in a new tab)
, and
Dataset License
(opens in a new tab)
ACCEPT & CONTINUE