Sciweavers

2047 search results - page 195 / 410
» The limits of speech recognition
Sort
View
ICASSP
2011
IEEE
13 years 1 months ago
Emotion classification from speech using evaluator reliability-weighted combination of ranked lists
In emotion recognition, a widely-used method to reconciliate disagreement between multiple human evaluators is to perform majority-voting on their assigned class labels. Instead, ...
Kartik Audhkhasi, Shrikanth S. Narayanan
PAMI
2012
12 years 18 days ago
A Tree-Based Context Model for Object Recognition
—There has been a growing interest in exploiting contextual information in addition to local features to detect and localize multiple object categories in an image. A context mod...
Myung Jin Choi, Antonio Torralba, Alan S. Willsky
WCE
2007
13 years 11 months ago
Face Recognition using Discrete Cosine Transform plus Linear Discriminant Analysis
—Face recognition is a biometric identification method which among the other methods such as, finger print identification, speech recognition, signature and hand written recognit...
M. Hajiarbabi, J. Askari, S. Sadri, M. Saraee
MICAI
2007
Springer
14 years 4 months ago
An EM Algorithm to Learn Sequences in the Wavelet Domain
The wavelet transform has been used for feature extraction in many applications of pattern recognition. However, in general the learning algorithms are not designed taking into acc...
Diego H. Milone, Leandro E. Di Persia
LREC
2010
188views Education» more  LREC 2010»
13 years 11 months ago
Example-Based Automatic Phonetic Transcription
Current state-of-the-art systems for automatic phonetic transcription (APT) are mostly phone recognizers based on Hidden Markov models (HMMs). We present a different approach for ...
Christina Leitner, Martin Schickbichler, Stefan Pe...