Results 51 to 60 of about 598 (156)

An Effective Respiratory Sound Endpoint Detection for Electronic Stethoscope Based on Machine Learning

IET Signal Processing, Volume 2025, Issue 1, 2025.
Compared to human speech and multimedia audio, the amplitude of lung respiratory sounds is extremely weak, with minimal differences between the respiratory sounds of various lung diseases. Traditional methods, such as Mel‐frequency cepstral coefficients (MFCCs) and the Fourier transform, struggle to accurately extract respiratory sound characteristics ...
Bo Hu, Runwei Chen, Weifeng Zhu, Jin Zhan, Dongying Zhang, JinPing Zheng, Jiajia Guo   +6 more
wiley   +1 more source

Thermally Stable Ag2Se Nanowire Network as an Effective In‐Materio Physical Reservoir Computing Device

Advanced Electronic Materials, Volume 10, Issue 12, December 2024.
This study explores a material physical reservoir called an in‐materio physical reservoir (IMRC) consisting of an Ag2Se nanowire network, computing to achieve efficient hardware. The Ag2Se device demonstrates the requisite characteristics of IMRC, including nonlinear switching, memory, and higher harmonic generation.
Takumi Kotooka, Sam Lilak, Adam Z. Stieg, James K. Gimzewski, Naoyuki Sugiyama, Yuichiro Tanaka, Takuya Kawabata, Ahmet Karacali, Hakaru Tamukoh, Yuki Usami, Hirofumi Tanaka   +10 more
wiley   +1 more source

Using auditory classification images for the identification of fine acoustic cues used in speech perception [PDF]

, 2013
International audienceAn essential step in understanding the processes underlying the general mechanism of perceptual categorization is to identify which portions of a physical stimulation modulate the behavior of our perceptual system. More specifically,
Hoen, Michel, Knoblauch, Kenneth, Meunier, Fanny, Varnet, Léo   +3 more
core   +5 more sources

A review of memristive reservoir computing for temporal data processing and sensing

InfoScience, Volume 1, Issue 1, December 2024.
This review explores memristive reservoir computing (RC) systems, highlighting device requirements, methods to enhance performance, and the recent development of energy‐efficient in‐sensor RC systems for machine vision. It also discusses the limitations and future directions for improving memristive and in‐sensor RC systems, emphasizing their potential
Yoon Ho Jang, Joon‐Kyu Han, Cheol Seong Hwang   +2 more
wiley   +1 more source

Multimodal spatio-temporal framework for real-world affect recognition

International Journal of Intelligent Networks
Deep learning models show great potential in applications involving video-based affect recognition, including human-computer interaction, robotic interfaces, stress and depression assessment, and Alzheimer's disease detection.
Karishma Raut, Sujata Kulkarni, Ashwini Sawant   +2 more
doaj   +1 more source

Efficient spike encoding algorithms for neuromorphic speech recognition

, 2022
Spiking Neural Networks (SNN) are known to be very effective for neuromorphic processor implementations, achieving orders of magnitude improvements in energy efficiency and computational latency over traditional deep learning approaches.
Rouat, Jean, Wood, Sean U. N., Yarga, Sidi Yaya Arnaud   +2 more
core   +1 more source

Experimental Demonstration of Reservoir Computing with Self‐Assembled Percolating Networks of Nanoparticles

Advanced Materials, Volume 36, Issue 29, July 18, 2024.
Brain‐like computing with percolating networks of nanoparticles. Successful spoken digit recognition is achieved by converting audio waveforms to electrical signals which are classified using a reservoir computing scheme. The use of parallel reservoirs results in state‐of‐the‐art accuracy.
Joshua B. Mallinson, Jamie K. Steel, Zachary E. Heywood, Sofie J. Studholme, Philip J. Bones, Simon A. Brown   +5 more
wiley   +1 more source

Using Visual Speech Information in Masking Methods for Audio Speaker Separation [PDF]

, 2018
This work examines whether visual speech infor- mation can be effective within audio masking-based speaker separation to improve the quality and intelligibility of the target speech.
Khan, Faheem, Le Cornu, Thomas, Milner, Ben P.   +2 more
core   +1 more source

Brain‐Inspired Organic Electronics: Merging Neuromorphic Computing and Bioelectronics Using Conductive Polymers

Advanced Functional Materials, Volume 34, Issue 15, April 10, 2024.
Polymer‐based organic electronics, featuring neuromorphic behavior and low voltage operation, provide energy‐efficient in‐memory computing as an alternative to conventional artificial intelligence. They support decentralized on‐chip learning and hold promise for closed‐loop intelligent systems.
Imke Krauhausen, Charles‐Théophile Coen, Simone Spolaor, Paschalis Gkoupidenis, Yoeri van de Burgt   +4 more
wiley   +1 more source

Parameter estimation of neuron models using in-vitro and in-vivo electrophysiological data [PDF]

, 2015
Spiking neuron models can accurately predict the response of neurons to somatically injected currents if the model parameters are carefully tuned. Predicting the response of in-vivo neurons responding to natural stimuli presents a far more challenging ...
Houghton, Conor J, Lynch, Eoin
core   +2 more sources