Deep learning on mobile devices: a review
Y Deng - Mobile Multimedia/Image Processing, Security, and …, 2019 - spiedigitallibrary.org
Recent breakthroughs in deep learning and artificial intelligence technologies have enabled
numerous mobile applications. While traditional computation paradigms rely on mobile …
numerous mobile applications. While traditional computation paradigms rely on mobile …
Isolated word recognition with the liquid state machine: a case study
D Verstraeten, B Schrauwen, D Stroobandt… - Information Processing …, 2005 - Elsevier
The Liquid State Machine (LSM) is a recently developed computational model with
interesting properties. It can be used for pattern classification, function approximation and …
interesting properties. It can be used for pattern classification, function approximation and …
Glimpse: A programmable early-discard camera architecture for continuous mobile vision
We consider the problem of continuous computer-vision based analysis of video streams
from mobile cameras over extended periods. Given high computational demands, general …
from mobile cameras over extended periods. Given high computational demands, general …
A developmental approach to structural self-organization in reservoir computing
J Yin, Y Meng, Y Jin - IEEE transactions on autonomous mental …, 2012 - ieeexplore.ieee.org
Reservoir computing (RC) is a computational framework for neural network based
information processing. Little work, however, has been conducted on adapting the structure …
information processing. Little work, however, has been conducted on adapting the structure …
听觉外周计算模型研究进展
李朝晖, 迟惠生 - 声学学报, 2006 - jac.ac.cn
在简单介绍听觉外周特性之后, 对近30 年听觉外周计算模型的研究及其在语音识别领域的应用
进行了评述, 针对未来语音信号处理领域中听觉外周的建模, 提出了一些设想; …
进行了评述, 针对未来语音信号处理领域中听觉外周的建模, 提出了一些设想; …
[PDF][PDF] Continuous feature adaptation for non-native speech recognition
The current speech interfaces in many military applications may be adequate for native
speakers. However, the recognition rate drops quite a lot for non-native speakers (people …
speakers. However, the recognition rate drops quite a lot for non-native speakers (people …
Extreme Learning Layer: A Boost for Spoken Digit Recognition with Spiking Neural Networks
I Peralta, N Odetti, HL Rufiner - International Conference on Speech and …, 2023 - Springer
The automatic recognition of speaker-independent digits requires high accuracy and
robustness to noise and variability. Spiking neural networks (SNNs) are a promising model …
robustness to noise and variability. Spiking neural networks (SNNs) are a promising model …
[PDF][PDF] Independent component analysis for environmentally robust speech recognition
D Kolossa - 2008 - depositonce.tu-berlin.de
Automatic speech recognition systems have seen a rapid development in recent years, and
in many cases they have evolved from prototypes to actually useful and productive tools …
in many cases they have evolved from prototypes to actually useful and productive tools …
[PDF][PDF] Recognition of isolated digits using a liquid state machine
D Verstraeten, B Schrauwen… - Proceedings of SPS …, 2005 - academia.edu
ABSTRACT The Liquid State Machine (LSM) is a recently developed computational model
[1] with interesting properties. It can be used for pattern classification, function approximation …
[1] with interesting properties. It can be used for pattern classification, function approximation …
[PDF][PDF] Identification of systematic differences in acoustic properties in categories of laughter in “MULTISIMO” dataset
M Shi - 2024 - researchgate.net
Research into laughter classification is a compelling field that captivates scientists and
sociologists seeking to unravel the enigmatic nature of this social signal. This paralinguistic …
sociologists seeking to unravel the enigmatic nature of this social signal. This paralinguistic …