19 search results - page 4 / 4 » Phoneme recognition in TIMIT with BLSTM-CTC |
COST
2007
Springer
13 years 11 months ago
2007
Springer
This paper is dedicated to the description and the study of a new feature extraction approach for emotion recognition. Our contribution is based on the extraction and the character...
ICASSP
2011
IEEE
12 years 9 months ago
2011
IEEE
In this paper, we present a novel technique for modeling the posterior probability estimates obtained from a neural network directly in the HMM framework using the Dirichlet Mixtu...
NOLISP
2005
Springer
13 years 10 months ago
2005
Springer
Feature projection by non-linear discriminant analysis (NLDA) can substantially increase classification performance. In automatic speech recognition (ASR) the projection provided b...
MICAI
2007
Springer
13 years 11 months ago
2007
Springer
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...