263 search results - page 20 / 53 » Whole-book recognition using mutual-entropy-driven model ada... |
INTERSPEECH
2010
13 years 5 months ago
2010
Linear regression based speaker adaptation approaches can improve Automatic Speech Recognition (ASR) accuracy significantly for a target speaker. However, when the available adapt...
ICASSP
2010
IEEE
13 years 11 months ago
2010
IEEE
This paper studies the influence of n-gram language models in the recognition of sung phonemes and words. We train uni-, bi-, and trigram language models for phonemes and bi- and...
GBRPR
2005
Springer
14 years 4 months ago
2005
Springer
Shock graphs have emerged as a powerful generic 2-D shape representation. However, most approaches typically assume that the silhouette has been correctly segmented. In this paper,...
EMNLP
2009
13 years 8 months ago
2009
In this paper, we present a semi-supervised method for automatic speech act recognition in email and forums. The major challenge of this task is due to lack of labeled data in the...
ICASSP
2008
IEEE
14 years 5 months ago
2008
IEEE
This paper describes a new method for fast speaker adaptation in large vocabulary recognition systems. As in most HMM-based recognizers, the observation densities are modeled as a...