Emerging artificial synaptic devices for neuromorphic computing
In today's era of big‐data, a new computing paradigm beyond today's von‐Neumann
architecture is needed to process these large‐scale datasets efficiently. Inspired by the …
architecture is needed to process these large‐scale datasets efficiently. Inspired by the …
Enhancements in automatic Kannada speech recognition system by background noise elimination and alternate acoustic modelling
G Thimmaraja Yadava, HS Jayanna - International Journal of Speech …, 2020 - Springer
In this paper, the improvements in the recently implemented Kannada speech recognition
system is demonstrated in detail. The Kannada automatic speech recognition (ASR) system …
system is demonstrated in detail. The Kannada automatic speech recognition (ASR) system …
Nonlinear system modeling and application based on restricted Boltzmann machine and improved BP neural network
J Qiao, L Wang - Applied Intelligence, 2021 - Springer
Aiming at the complexity, nonlinearity and difficulty in modeling of nonlinear system. In this
paper, an improved back-propagation (BP) neural network based on restricted boltzmann …
paper, an improved back-propagation (BP) neural network based on restricted boltzmann …
Continuous Kannada speech recognition system under degraded condition
PS Praveen Kumar, G Thimmaraja Yadava… - Circuits, Systems, and …, 2020 - Springer
In this paper, a continuous Kannada speech recognition system is developed under different
noisy conditions. The continuous Kannada speech sentences are collected from 2400 …
noisy conditions. The continuous Kannada speech sentences are collected from 2400 …
Real-time prediction of tumor motion using a dynamic neural network
M Mafi, SM Moghadam - Medical & biological engineering & computing, 2020 - Springer
Radiation dose delivery into the thoracic and abdomen cavities during radiotherapy
treatment is a challenging task as respiratory motion leads to the motion of the target tumor …
treatment is a challenging task as respiratory motion leads to the motion of the target tumor …
Heterogeneous reservoir computing models for persian speech recognition
Z Ansari, F Pourhoseini… - 2022 International Joint …, 2022 - ieeexplore.ieee.org
Over the last decade, deep-learning methods have been gradually incorporated into
conventional automatic speech recognition (ASR) frameworks to create acoustic …
conventional automatic speech recognition (ASR) frameworks to create acoustic …
Multilevel weight optimization of photonic synapses based on slot-ridge waveguides with multi-block GST
H Zhang, B Huang, Z Zhang, C Cheng, Z Zhang… - Optics …, 2024 - Elsevier
Neuromorphic computing has been a candidate to work like human brains to deal with big
data energy-efficiently beyond the von Neumann architecture. As an important part, artificial …
data energy-efficiently beyond the von Neumann architecture. As an important part, artificial …
A self-organizing deep belief network based on information relevance strategy
YX Wang, HG Han, M Guo, JF Qiao - Neurocomputing, 2020 - Elsevier
One of the major obstacles in using deep belief network (DBN) is the structure design.
Numerous studies, both empirically and theoretically, show that choosing suitable structure …
Numerous studies, both empirically and theoretically, show that choosing suitable structure …
Persian Language Phone Recognition Based on Robust Extraction of Acoustic Landmarks
S Reza, SA Seyyedsalehi… - 2020 27th National and …, 2020 - ieeexplore.ieee.org
Acoustic landmarks are defined as more informative parts of the speech signal and are
proofed to be beneficial in designing more robust speech recognition systems. This work …
proofed to be beneficial in designing more robust speech recognition systems. This work …
Automation of the Spoken Poetry Rhyming Game in Persian
M Bijankhan, H Veisi - International Journal of Information Science and …, 2023 - ijism.isc.ac
This paper aims to investigate how a Persian spoken poetry game, called Mosha'ere, can be
computerized by using a Persian automatic speech recognition system trained with read …
computerized by using a Persian automatic speech recognition system trained with read …