Sciweavers

Share
warning: Creating default object from empty value in /var/www/modules/taxonomy/taxonomy.module on line 1416.
ICASSP
2011
IEEE
9 years 7 months ago
A basis method for robust estimation of constrained MLLR
Constrained Maximum Likelihood Linear Regression (CMLLR) is a widely used speaker adaptation technique in which an affine transform of the features is estimated for each speaker....
Daniel Povey, Kaisheng Yao
ICASSP
2011
IEEE
9 years 8 months ago
Rapid joint speaker and noise compensation for robust speech recognition
For speech recognition, mismatches between training and testing for speaker and noise are normally handled separately. The work presented in this paper aims at jointly applying sp...
K. K. Chin, Haitian Xu, Mark J. F. Gales, Catherin...
ICASSP
2011
IEEE
9 years 8 months ago
Using stacked transformations for recognizing foreign accented speech
A common problem in speech recognition for foreign accented speech is that there is not enough training data for an accent-specific or a speaker-specific recognizer. Speaker ada...
Peter Smit, Mikko Kurimo
ICASSP
2011
IEEE
9 years 8 months ago
Defining the controlling parameter in constrained discriminative linear transform for supervised speaker adaptation
Constrained discriminative linear transform (CDLT) optimized with Extended Baum-Welch (EBW) has been presented in the literature as a discriminative speaker adaptation method that...
Danning Jiang, Dimitri Kanevsky, Emmanuel Yashchin...
ICASSP
2011
IEEE
9 years 8 months ago
An investigation of subspace modeling for phonetic and speaker variability in automatic speech recognition
This paper investigates the impact of subspace based techniques for acoustic modeling in automatic speech recognition (ASR). There are many well known approaches to subspace based...
Richard C. Rose, Shou-Chun Yin, Yun Tang
INTERSPEECH
2010
9 years 11 months ago
Discriminative adaptation for log-linear acoustic models
Log-linear models have recently been used in acoustic modeling for speech recognition systems. This has been motivated by competitive results compared to systems based on Gaussian...
Jonas Lööf, Ralf Schlüter, Hermann ...
INTERSPEECH
2010
9 years 11 months ago
The RWTH 2009 quaero ASR evaluation system for English and German
In this work, the RWTH automatic speech recognition systems for English and German for the second Quaero evaluation campaign 2009 are presented. The systems are designed to transc...
Markus Nußbaum-Thom, Simon Wiesler, Martin S...
INTERSPEECH
2010
9 years 11 months ago
Regularized-MLLR speaker adaptation for computer-assisted language learning system
In this paper, we propose a novel speaker adaptation technique, regularized-MLLR, for Computer Assisted Language Learning (CALL) systems. This method uses a linear combination of ...
Dean Luo, Yu Qiao, Nobuaki Minematsu, Yutaka Yamau...
ICASSP
2009
IEEE
10 years 1 months ago
A new method for speaker adaptation using bilinear model
In this paper, a novel method for speaker adaptation using bilinear model is proposed. Bilinear model can express both characteristics of speakers (style) and phonemes across spea...
Hwa Jeon Song, Yongwon Jeong, Hyung Soon Kim
TASLP
2002
96views more  TASLP 2002»
10 years 3 months ago
MAP speaker adaptation of state duration distributions for speech recognition
This paper presents a framework for maximum a posteriori (MAP) speaker adaptation of state duration distributions in hidden Markov models (HMM). Four key issues of MAP estimation, ...
Néstor Becerra Yoma, Jorge Silva Sán...
books