2629 search results - page 343 / 526 » Components for Face Recognition |
145
click to vote
DAGSTUHL
1994
15 years 7 months ago
1994
Functionality-based recognition systems recognize objects at the category level by reasoning about how well the objects support the expected function. Such systems naturally assoc...
164
click to vote
CSL
2007
Springer
15 years 6 months ago
2007
Springer
Hidden Markov Models (HMMs) are the most commonly used acoustic model for speech recognition. In HMMs, the probability of successive observations is assumed independent given the ...
148
click to vote
CSL
2000
Springer
15 years 6 months ago
2000
Springer
This paper introduces a new form of observation distributions for hidden Markov models (HMMs), combining subvector quantization and mixtures of discrete distrib utions. Despite w...
157
click to vote
INTERSPEECH
2010
15 years 1 months ago
2010
Information retrieval methods are frequently used for indexing and retrieving spoken documents, and more recently have been proposed for voice-search amongst a pre-defined set of ...
180
click to vote
ICASSP
2011
IEEE
2011
IEEE
A wavelet-based data imputation approach to spectrogram reconstruction for robust speech recognition
14 years 10 months ago
Data imputation approaches for robust automatic speech recognition reconstruct noise corrupted spectral information by exploiting prior knowledge of the relationship between targe...