376 search results - page 29 / 76 » Analysis-by-synthesis features for speech recognition |
ICASSP
2009
IEEE
14 years 4 months ago
2009
IEEE
We introduce a direct model for speech recognition that assumes an unstructured, i.e., flat text output. The flat model allows us to model arbitrary attributes and dependences o...
CSL
2004
Springer
13 years 9 months ago
2004
Springer
Recently various techniques to improve the correlation model of feature vector elements in speech recognition systems have been proposed. Such techniques include semi-tied covaria...
ICASSP
2008
IEEE
14 years 4 months ago
2008
IEEE
Defining suitable features for environmental sounds is an important problem in an automatic acoustic scene recognition system. As with most pattern recognition problems, extracti...
ACII
2007
Springer
14 years 3 months ago
2007
Springer
Abstract. Opposing the pre-dominant turn-wise statistics of acoustic LowLevel-Descriptors followed by static classification we re-investigate dynamic modeling directly on the frame...
INTERSPEECH
2010
13 years 4 months ago
2010
Log-linear models have recently been used in acoustic modeling for speech recognition systems. This has been motivated by competitive results compared to systems based on Gaussian...