Sciweavers

29 search results - page 1 / 6
» Detection-based speech recognition with sparse point process...
Sort
View
ICASSP
2011
IEEE
12 years 8 months ago
Whole word discriminative point process models
This paper introduces a discriminative extension to whole-word point process modeling techniques. Meant to circumvent the strong independence assumptions of their generative prede...
Aren Jansen
ICASSP
2008
IEEE
13 years 11 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
2010
IEEE
13 years 5 months ago
Learning with synthesized speech for automatic emotion recognition
Data sparseness is an ever dominating problem in automatic emotion recognition. Using artificially generated speech for training or adapting models could potentially ease this: t...
Bjoern Schuller, Felix Burkhardt