21 search results - page 4 / 5 » Combining Spectral Representations for Large-Vocabulary Cont... |
GW
2007
Springer
14 years 2 months ago
2007
Springer
Abstract. In automatic sign language translation, one of the main problems is the usage of spatial information in sign language and its proper representation and translation, e.g. ...
INTERSPEECH
2010
13 years 3 months ago
2010
State-of-the-art large vocabulary continuous speech recognition (LVCSR) systems often combine outputs from multiple subsystems developed at different sites. Cross system adaptatio...
ICASSP
2010
IEEE
13 years 8 months ago
2010
IEEE
In discriminative training, such as Maximum Mutual Information Estimation (MMIE) training, a word lattice is usually used as a compact representation of many different sentence hy...
ICMCS
2005
IEEE
14 years 2 months ago
2005
IEEE
A new framework for the context and speaker independent recognition of emotions from voice, based on a richer and more natural representation of the speech signal, is proposed. Th...
ICASSP
2008
IEEE
14 years 3 months ago
2008
IEEE
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...