283 search results - page 5 / 57 » Phoneme recognition using Boosted Binary Features |
ICASSP
2011
IEEE
12 years 11 months ago
2011
IEEE
Hidden Conditional Random Fields(HCRF) is a very promising approach to model speech. However, because HCRF computes the score of a hypothesis by summing up linearly weighted featu...
IWBRS
2005
Springer
14 years 29 days ago
2005
Springer
Though AdaBoost has been widely used for feature selection and classifier learning, many of the selected features, or weak classifiers, are redundant. By incorporating mutual infor...
ICASSP
2011
IEEE
12 years 11 months ago
2011
IEEE
Phoneme posterior probabilities estimated using Multi-Layer Perceptrons (MLPs) are extensively used both as acoustic scores and features for speech recognition. In this paper we e...
ICASSP
2010
IEEE
13 years 7 months ago
2010
IEEE
The standard approach to speaker verification is to extract cepstral features from the speech spectrum and model them by generative or discriminative techniques. We propose a nov...
INTERSPEECH
2010
13 years 2 months ago
2010
In an attempt to improve models of human perception, the recognition of phonemes in nonsense utterances was predicted with automatic speech recognition (ASR) in order to analyze i...