Sciweavers

121 search results - page 5 / 25
» Corrected tandem features for acoustic model training
Sort
View
AMDO
2006
Springer
13 years 11 months ago
Automatic Pose Correction for Local Feature-Based Face Authentication
In this paper, we present an automatic face authentication system. Accurate segmentation of prominent facial features is accomplished by means of an extension of the Active Shape M...
Daniel González-Jiménez, Federico Su...
MLMI
2005
Springer
14 years 1 months ago
Hierarchical Multi-stream Posterior Based Speech Recognition System
Abstract. In this paper, we present initial results towards boosting posterior based speech recognition systems by estimating more informative posteriors using multiple streams of ...
Hamed Ketabdar, Hervé Bourlard, Samy Bengio
ICASSP
2011
IEEE
12 years 11 months ago
Preserve ordering property of generated LSPS for minimum generation error training in HMM-based speech synthesis
Ordering property is an important property of LSP and closely connected with the naturalness of reconstructed speech. When LSP is adopted as spectrum feature in HMM-based parametr...
Ming Lei, Zhen-Hua Ling, Li-Rong Dai
ICPR
2006
IEEE
14 years 8 months ago
Pose Correction and Subject-Specific Features for Face Authentication
In this paper, we present a face authentication system that can be broken down in three stages. Prior to feature extraction, a pose correction step is applied, so that frontal fac...
Daniel González-Jiménez, José...
NAACL
2010
13 years 5 months ago
Using Mostly Native Data to Correct Errors in Learners' Writing
We present results from a range of experiments on article and preposition error correction for non-native speakers of English. We first compare a language model and errorspecific ...
Michael Gamon