scholarly journals Future directions in speech information processing

1998 ◽  
Vol 103 (5) ◽  
pp. 2747-2747
Author(s):  
Sadaoki Furui
Keyword(s):  
Information Processing ◽  
Future Directions ◽  
Speech Information

Optimization of ANN Based on EA

2011 ◽  
Vol 271-273 ◽  
pp. 629-632
Author(s):  
Hong Guo Zhu ◽  
Hai Xin ◽  
Chang Wen Zheng
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Information Processing ◽  
Evolutionary Algorithm ◽  
Future Directions ◽  
Existing Problems ◽  
Artificial Neural ◽  
Artificial Neural Network Ann

Artificial neural network (ANN) and evolutionary algorithm (EA) are both biology-based models of information processing. The basic theories of ANN and EA are described. Then the mechanisms of using EA for ANN’s optimization are explained and the research states are summarized. The existing problems and future directions are demonstrated finally.

Tactile Cuing to Augment Multisensory Human-Machine Interaction

2015 ◽  
Vol 23 (2) ◽  
pp. 4-9 ◽  
Author(s):  
Peter A. Hancock ◽  
Ben Lawson ◽  
Roger Cholewiak ◽  
Linda R. Elliott ◽  
Jan B. F. van Erp ◽  
...  
Keyword(s):  
Information Processing ◽  
Processing Capacity ◽  
Human Machine Interaction ◽  
Future Directions ◽  
Auditory Displays ◽  
Information Processing Capacity ◽  
Tactile Displays ◽  
Machine Interaction

Tactile displays promise to improve the information-processing capacity of operators, especially when used in conjunction with visual and auditory displays. In this article, we describe current applications and future directions in tactile cuing.

scholarly journals A tutorial survey of architectures, algorithms, and applications for deep learning

2014 ◽  
Vol 3 ◽  
Author(s):  
Li Deng
Keyword(s):  
Deep Learning ◽  
Information Processing ◽  
Language Processing ◽  
Feature Learning ◽  
Representation Learning ◽  
Machine Learning Techniques ◽  
Major Work ◽  
Future Directions ◽  
Recent Developments ◽  
History Of

In this invited paper, my overview material on the same topic as presented in the plenary overview session of APSIPA-2011 and the tutorial material presented in the same conference [1] are expanded and updated to include more recent developments in deep learning. The previous and the updated materials cover both theory and applications, and analyze its future directions. The goal of this tutorial survey is to introduce the emerging area of deep learning or hierarchical learning to the APSIPA community. Deep learning refers to a class of machine learning techniques, developed largely since 2006, where many stages of non-linear information processing in hierarchical architectures are exploited for pattern classification and for feature learning. In the more recent literature, it is also connected to representation learning, which involves a hierarchy of features or concepts where higher-level concepts are defined from lower-level ones and where the same lower-level concepts help to define higher-level ones. In this tutorial survey, a brief history of deep learning research is discussed first. Then, a classificatory scheme is developed to analyze and summarize major work reported in the recent deep learning literature. Using this scheme, I provide a taxonomy-oriented survey on the existing deep architectures and algorithms in the literature, and categorize them into three classes: generative, discriminative, and hybrid. Three representative deep architectures – deep autoencoders, deep stacking networks with their generalization to the temporal domain (recurrent networks), and deep neural networks (pretrained with deep belief networks) – one in each of the three classes, are presented in more detail. Next, selected applications of deep learning are reviewed in broad areas of signal and information processing including audio/speech, image/vision, multimodality, language modeling, natural language processing, and information retrieval. Finally, future directions of deep learning are discussed and analyzed.

scholarly journals Hemispheric association and dissociation of voice and speech information processing in stroke

Cortex ◽  
2015 ◽  
Vol 71 ◽  
pp. 232-239 ◽  
Author(s):  
Anna B. Jones ◽  
Andrew J. Farrall ◽  
Pascal Belin ◽  
Cyril R. Pernet
Keyword(s):  
Information Processing ◽  
Speech Information ◽  
Voice And Speech

scholarly journals Information Processing in PTSD: Evidence for Biased Attentional, Interpretation, and Memory Processes

2016 ◽  
Vol a4 (3) ◽  
pp. 218-243 ◽  
Author(s):  
Jessica Bomyea ◽  
Alyson Johnson ◽  
Ariel J. Lang
Keyword(s):  
Posttraumatic Stress Disorder ◽  
Information Processing ◽  
Stress Disorder ◽  
Memory Studies ◽  
Key Factors ◽  
Future Directions ◽  
Comprehensive Review ◽  
Information Processing Biases ◽  
Interpretation Biases ◽  
Subjective Risk

This comprehensive review surveys current literature on information processing biases in posttraumatic stress disorder (PTSD). The review is organized by information processing systems including attention, judgment and interpretation, and memory. Studies outlined suggest that information processing biases may be key factors involved in the development and maintenance of PTSD. However, inconsistencies exist in the literature within each domain, often depending on assessment paradigm employed or other methodological features. Studies on attention bias demonstrate both facilitated engagement toward and difficulty disengaging from threatening stimuli. Literature on judgment and interpretation biases indicates that those with PTSD are more likely to interpret ambiguous situations as threatening, in addition to over-estimating subjective risk. Memory studies reveal mixed findings; a number of studies found that those with PTSD exhibit a bias toward remembering trauma-relevant or negative stimuli compared to those without PTSD, while others do not replicate this effect. Existing evidence for information processing biases in each of these domains are integrated and future directions for empirical study outlined.

Sign in / Sign up

Export Citation Format

Share Document