Sciweavers

7413 search results - page 484 / 1483
» Using Specularities for Recognition
Sort
View
ICDAR
2009
IEEE
15 years 4 months ago
Two-stage Approach for Word-wise Script Identification
A two-stage approach for word-wise identification of English (Roman), Devnagari and Bengali (Bangla) scripts is proposed. This approach balances the tradeoff between recognition a...
Sukalpa Chanda, Srikanta Pal, Katrin Franke, Umapa...
INTERSPEECH
2010
15 years 1 months ago
Learning from human errors: prediction of phoneme confusions based on modified ASR training
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...
Bernd T. Meyer, Birger Kollmeier
TNN
2010
227views Management» more  TNN 2010»
15 years 1 months ago
Self-Organizing MultiLayer Perceptron
Abstract--A set of Artificial Neural Network (ANN) based methods for the design of an effective system of speech recognition of numerals of Assamese language captured under varied ...
B. Gas
ICASSP
2011
IEEE
14 years 10 months ago
Machine and acoustical condition dependency analyses for fast acoustic likelihood calculation techniques
The acceleration of acoustic likelihood calculation has been an important research issue for developing practical speech recognition systems. And there are various specification ...
Atsunori Ogawa, Satoshi Takahashi, Atsushi Nakamur...
ECCV
2006
Springer
16 years 9 months ago
Weakly Supervised Learning of Part-Based Spatial Models for Visual Object Recognition
Abstract. In this paper we investigate a new method of learning partbased models for visual object recognition, from training data that only provides information about class member...
David J. Crandall, Daniel P. Huttenlocher