Skip to search formSkip to main content
You are currently offline. Some features of the site may not work correctly.

FMLLR

Feature space Maximum Likelihood Linear Regression (fMLLR) is a widely used technique for speaker adaptation in HMM-based speech recognition.
Wikipedia

Related topics

Related topics

5 relations

Broader (2)

Automatic identification and data captureSpeech recognition
Feature scalingHidden Markov modelKernel eigenvoice

Papers overview

Semantic Scholar uses AI to extract papers important to this topic.
2016
2016
DNNs for Unsupervised Extraction of Pseudo FMLLR Features Without Explicit Adaptation Data
In this paper, we propose the use of deep neural networks (DNN) as a regression model to estimate feature-space maximum… Expand
  • figure 1
  • figure 2
  • figure 3
  • figure 4
  • table 1
2016
2016
Differentiable Pooling for Unsupervised Acoustic Model Adaptation
We present a deep neural network (DNN) acoustic model that includes parametrised and differentiable pooling operators… Expand
  • figure 1
  • figure 2
  • table I
  • figure 3
  • table III
2014
2014
Unfolded recurrent neural networks for speech recognition
We introduce recurrent neural networks (RNNs) for acoustic modeling which are unfolded in time for a fixed number of time steps… Expand
  • figure 1
  • figure 2
  • figure 3
  • figure 4
  • table 1
Highly Cited
2013
Highly Cited
2013
Improvements to Deep Convolutional Neural Networks for LVCSR
Deep Convolutional Neural Networks (CNNs) are more powerful than Deep Neural Networks (DNN), as they are able to better reduce… Expand
  • table 1
  • table 4
  • table 2
  • table 3
  • table 5
Highly Cited
2013
Highly Cited
2013
Speaker adaptation of neural network acoustic models using i-vectors
We propose to adapt deep neural network (DNN) acoustic models to a target speaker by supplying speaker identity vectors (i… Expand
  • figure 1
  • figure 2
  • table II
  • table I
2012
2012
Initialization of adaptation by sufficient statistics using phonetic tree
In this work we deal with the problem of small amount of data when estimating a feature transformation for the speaker adaptation… Expand
  • figure 1
  • figure 2
  • figure 3
  • table I
2012
2012
A factorized representation of FMLLR transform based on QR-decomposition
In this paper, we propose a novel representation of the FMLLR transform. This is different from the standard FMLLR in that the… Expand
  • table 1
  • table 2
2011
2011
Initialization of fMLLR with Sufficient Statistics from Similar Speakers
One of the most utilized adaptation techniques is the feature Maximum Likelihood Linear Regression (fMLLR). In comparison with… Expand
  • figure 1
  • table 1
  • figure 2
2009
2009
Refinement Approach for Adaptation Based on Combination of MAP and fMLLR
This paper deals with a combination of basic adaptation techniques of Hidden Markov Model used in the speech recognition. The… Expand
  • table 1
  • figure 1
2008
2008
Quick fmllr for speaker adaptation in speech recognition
Feature space maximum likelihood linear regression (fMLLR) is a widely used technique for speaker adaptation in HMM-based speech… Expand
  • table 1
  • figure 1
By clicking accept or continuing to use the site, you agree to the terms outlined in our Privacy Policy, Terms of Service, and Dataset License
ACCEPT & CONTINUE