Sciweavers

Share
ICASSP
2011
IEEE
8 years 3 months ago
Lattice-based unsupervised acoustic model training
Unsupervised acoustic model training has been successfully used to improve the performance of automatic speech recognition systems when only a small amount of manually transcribed...
Thiago Fraga-Silva, Jean-Luc Gauvain, Lori Lamel
ICASSP
2011
IEEE
8 years 3 months ago
A kernelized maximal-figure-of-merit learning approach based on subspace distance minimization
We propose a kernelized maximal-figure-of-merit (MFoM) learning approach to efficiently training a nonlinear model using subspace distance minimization. In particular, a fixed,...
Byungki Byun, Chin-Hui Lee
ICASSP
2011
IEEE
8 years 3 months ago
Distributed training of large scale exponential language models
Shrinkage-based exponential language models, such as the recently introduced Model M, have provided significant gains over a range of tasks [1]. Training such models requires a l...
Abhinav Sethy, Stanley F. Chen, Bhuvana Ramabhadra...
TNN
2010
176views Management» more  TNN 2010»
8 years 6 months ago
On the weight convergence of Elman networks
Abstract--An Elman network (EN) can be viewed as a feedforward (FF) neural network with an additional set of inputs from the context layer (feedback from the hidden layer). Therefo...
Qing Song
TLT
2010
72views more  TLT 2010»
8 years 6 months ago
Quantifying Effects of Exposure to the Third and First-Person Perspectives in Virtual-Reality-Based Training
In the recent years, usage of the third-person perspective (3PP) in virtual training methods has become increasingly viable and despite the growing interest in virtual reality and ...
Patrick Salamin, Tej Tadi, Olaf Blanke, Fré...
PROMISE
2010
8 years 6 months ago
On the value of learning from defect dense components for software defect prediction
BACKGROUND: Defect predictors learned from static code measures can isolate code modules with a higher than usual probability of defects. AIMS: To improve those learners by focusi...
Hongyu Zhang, Adam Nelson, Tim Menzies
JMLR
2010
169views more  JMLR 2010»
8 years 6 months ago
Consensus-Based Distributed Support Vector Machines
This paper develops algorithms to train support vector machines when training data are distributed across different nodes, and their communication to a centralized processing unit...
Pedro A. Forero, Alfonso Cano, Georgios B. Giannak...
INTERSPEECH
2010
8 years 6 months ago
Incremental word learning using large-margin discriminative training and variance floor estimation
We investigate incremental word learning in a Hidden Markov Model (HMM) framework suitable for human-robot interaction. In interactive learning, the tutoring time is a crucial fac...
Irene Ayllón Clemente, Martin Heckmann, Ale...
INTERSPEECH
2010
8 years 6 months ago
Learning from human errors: prediction of phoneme confusions based on modified ASR training
In an attempt to improve models of human perception, the recognition of phonemes in nonsense utterances was predicted with automatic speech recognition (ASR) in order to analyze i...
Bernd T. Meyer, Birger Kollmeier
CVPR
2011
IEEE
8 years 7 months ago
Shared Parts for Deformable Part-based Models
The deformable part-based model (DPM) proposed by Felzenszwalb et al. has demonstrated state-of-the-art results in object localization. The model offers a high degree of learnt in...
Patrick Ott
books