Sciweavers

2047 search results - page 61 / 410
» The limits of speech recognition
Sort
View
INTERSPEECH
2010
13 years 3 months ago
Exploring recognition network representations for efficient speech inference on highly parallel platforms
The emergence of highly parallel computing platforms is enabling new trade-offs in algorithm design for automatic speech recognition. It naturally motivates the following investig...
Jike Chong, Ekaterina Gonina, Kisun You, Kurt Keut...
SIBGRAPI
2005
IEEE
14 years 2 months ago
A Maximum Uncertainty LDA-Based Approach for Limited Sample Size Problems : With Application to Face Recognition
A critical issue of applying Linear Discriminant Analysis (LDA) is both the singularity and instability of the within-class scatter matrix. In practice, particularly in image recog...
Carlos E. Thomaz, Duncan Fyfe Gillies
ACL
2010
13 years 6 months ago
Personalising Speech-To-Speech Translation in the EMIME Project
In the EMIME project we have studied unsupervised cross-lingual speaker adaptation. We have employed an HMM statistical framework for both speech recognition and synthesis which p...
Mikko Kurimo, William Byrne, John Dines, Philip N....
ICASSP
2011
IEEE
13 years 13 days ago
Subspace pursuit method for kernel-log-linear models
This paper presents a novel method for reducing the dimensionality of kernel spaces. Recently, to maintain the convexity of training, loglinear models without mixtures have been u...
Yotaro Kubo, Simon Wiesler, Ralf Schlüter, He...
ICASSP
2011
IEEE
13 years 13 days ago
Pronunciation variants generation using SMT-inspired approaches
Enriching a pronunciation dictionary with phonological variation is a challenging task, not yet solved despite several decades of research, in particular for speech-to-text transc...
Panagiota Karanasou, Lori Lamel