Sciweavers

62 search results - page 8 / 13
» MAP-Based Perceptual Modeling for Noisy Speech Recognition
Sort
View
129
Voted
ICASSP
2008
IEEE
15 years 4 months ago
Unsupervised learning of auditory filter banks using non-negative matrix factorisation
Non-negative matrix factorisation (NMF) is an unsupervised learning technique that decomposes a non-negative data matrix into a product of two lower rank non-negative matrices. Th...
Alexander Bertrand, Kris Demuynck, Veronique Stout...
ICASSP
2008
IEEE
15 years 4 months ago
Multi-stream parameterization for structural speech recognition
Recently, a novel and structural representation of speech was proposed [1, 2], where the inevitable acoustic variations caused by nonlinguistic factors are effectively removed fro...
Satoshi Asakawa, Nobuaki Minematsu, Keikichi Hiros...
ICASSP
2009
IEEE
15 years 5 months ago
Bounded conditional mean imputation with Gaussian mixture models: A reconstruction approach to partly occluded features
In this work we show how conditional mean imputation can be bounded through the use of box-truncated Gaussian distributions. That is of interest when signals or features are partl...
Friedrich Faubel, John W. McDonough, Dietrich Klak...
83
Voted
TASLP
2002
96views more  TASLP 2002»
14 years 10 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...
ICASSP
2011
IEEE
14 years 2 months ago
Gammatone sub-band magnitude-domain dereverberation for ASR
We present an algorithm for dereverberation of speech signals for automatic speech recognition (ASR) applications. Often ASR systems are presented with speech that has been record...
Kshitiz Kumar, Rita Singh, Bhiksha Raj, Richard M....