Sciweavers

460 search results - page 18 / 92
» Introduction to speech recognition using neural networks
Sort
View
EUROMICRO
2000
IEEE
14 years 1 months ago
Tumor Recognition in Endoscopic Video Images Using Artificial Neural Network Architectures
This paper focuses on a scheme for automated tumor recognition using images acquired during endoscopic sessions. The proposed recognition system is based on multi-layer feed forwa...
S. A. Karkanis, Dimitrios K. Iakovidis, Dimitrios ...
ISNN
2011
Springer
12 years 11 months ago
Robust Multi-stream Keyword and Non-linguistic Vocalization Detection for Computationally Intelligent Virtual Agents
Abstract. Systems for keyword and non-linguistic vocalization detection in conversational agent applications need to be robust with respect to background noise and different speak...
Martin Wöllmer, Erik Marchi, Stefano Squartin...
IKE
2008
13 years 10 months ago
Text-independent Speaker Identification Based on MAP Channel Compensation and Pitch-dependent Features
One major source of performance decline in speaker recognition system is channel mismatch between training and testing. This paper focuses on improving channel robustness of speake...
JiQing Han, RongChun Gao
ICASSP
2011
IEEE
13 years 18 days ago
Speech inversion: Benefits of tract variables over pellet trajectories
Speech inversion is a way of estimating articulatory trajectories or vocal tract configurations from the acoustic speech signal. Traditionally, articulator flesh-point or pellet t...
Vikramjit Mitra, Hosung Nam, Carol Y. Espy-Wilson,...
IJCNN
2006
IEEE
14 years 2 months ago
Adaptation of Artificial Neural Networks Avoiding Catastrophic Forgetting
— In connectionist learning, one relevant problem is “catastrophic forgetting” that may occur when a network, trained with a large set of patterns, has to learn new input pat...
Dario Albesano, Roberto Gemello, Pietro Laface, Fr...