Sciweavers

7413 search results - page 573 / 1483
» Using Specularities for Recognition
Sort
View
207
Voted
ICASSP
2009
IEEE
16 years 2 months ago
Interpolating hidden Markov model and its application to automatic instrument recognition
This paper proposes an interpolating extension to hidden Markov models (HMMs), which allows more accurate modeling of natural sounds sources. The model is able to produce observat...
Tuomas Virtanen, Toni Heittola
200
Voted
ICDAR
2009
IEEE
16 years 2 months ago
A Probabilistic Framework for Soft Target Learning in Online Cursive Handwriting Recognition
To develop effective learning algorithms for online cursive word recognition is still a challenge research issue. In this paper, we propose a probabilistic framework to model the ...
Xiaoyuan Zhu, Yong Ge, Feng-Jun Guo, Li-Xin Zhen
156
Voted
ICASSP
2008
IEEE
16 years 1 months ago
Parsing-based objective functions for speech recognition in translation applications
This paper looks at a parsing-based alternative to word error rate (WER) for optimizing recognition, SParseval, hypothesizing that it may be a better objective for applications su...
Dustin Hillard, Mei-Yuh Hwang, Mary P. Harper, Mar...
181
Voted
ICASSP
2008
IEEE
16 years 1 months ago
Exploiting contextual information for improved phoneme recognition
In this paper, we investigate the significance of contextual information in a phoneme recognition system using the hidden Markov model - artificial neural network paradigm. Cont...
Joel Pinto, B. Yegnanarayana, Hynek Hermansky, Mat...
181
Voted
ICASSP
2008
IEEE
16 years 1 months ago
A covariance kernel for SVM language recognition
Discriminative training for language recognition has been a key tool for improving system performance. In addition, recognition directly from shifted-delta cepstral features has p...
William M. Campbell