Abstract | ||
---|---|---|
This paper describes ANN based posterior estimates and their application to speech recognition. We replaced the standard back-propagation with the L-BFGS quasi-Newton method. We have focused only on posterior based feature vector extraction. Our goal was a feature vector dimension reduction. Thus we designed three posterior transforms to space with dimensionality 1 or 2. The designed transforms were tested on the SpeechDat-East corpus. We also applied the introduced method on a Czech audio-visual corpus. In both cases the methods leads to significant word error rate decrease. |
Year | DOI | Venue |
---|---|---|
2010 | 10.1007/978-3-642-15760-8_61 | TSD |
Keywords | Field | DocType |
feature vector dimension reduction,speech recognition,feature vector extraction,significant word error rate,standard back-propagation,l-bfgs quasi-newton method,czech audio-visual corpus,speechdat-east corpus,posterior estimate,word error rate,quasi newton method,feature vector,back propagation,artificial neural network,dimension reduction | Czech,Feature vector,Dimensionality reduction,Pattern recognition,Computer science,Word error rate,Speech recognition,Curse of dimensionality,Artificial intelligence,Artificial neural network | Conference |
Volume | ISSN | ISBN |
6231 | 0302-9743 | 3-642-15759-9 |
Citations | PageRank | References |
0 | 0.34 | 10 |
Authors | ||
4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Jan Zelinka | 1 | 37 | 8.86 |
Luboý ýmídl | 2 | 3 | 0.84 |
Jan Trmal | 3 | 235 | 20.91 |
Luděk Müller | 4 | 75 | 10.67 |