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...
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 ...
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...
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...
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...