Results 61 to 70 of about 83,689 (283)

End-to-End Speech Recognition from the Raw Waveform [PDF]

Interspeech 2018, 2018
State-of-the-art speech recognition systems rely on fixed, hand-crafted features such as mel-filterbanks to preprocess the waveform before the training pipeline. In this paper, we study end-to-end systems trained directly from the raw waveform, building on two alternatives for trainable replacements of mel-filterbanks that use a convolutional ...
Zeghidour, Neil, Usunier, Nicolas, Synnaeve, Gabriel, Collobert, Ronan, Dupoux, Emmanuel   +4 more
openaire   +2 more sources

Actuating and Sensing Composites of Liquid Crystal Elastomers and Poly(ionic liquid)s

Advanced Functional Materials, EarlyView.
Ionic conductive, mechanically tough, flexible, and stretchable filaments of a composite material comprising a liquid crystal elastomer and a poly(ionic liquid) are produced through 3D printing, which exhibit large actuation strain under stimulation and electrical resistance variation in response to deformation or environmental condition changes. Their
Zeping Liu, Xiaofeng Zheng, Shaoxia Zhang, Long Xu, Meng Liu, Jeremy Baribeault St‐Germain, Yue Zhao   +6 more
wiley   +1 more source

Radar Waveform Recognition With ConvNeXt and Focal Loss

IEEE Access
A method of automatic recognition of radar waves based on time-frequency analysis (TFA) and ConvNeXt model is proposed in the paper. The method aims to address the challenges of feature extraction difficulty and low recognition correctness in complex ...
Liping Luo, Jie Huang, Yang Yang, Dexiu Hu   +3 more
doaj   +1 more source

Identify incipient faults through similarity comparison with waveform split-recognition framework

Frontiers in Energy Research, 2023
Introduction: Incipient faults of distribution networks, if not detected at an early stage, could evolve into permanent faults and result in significant economic losses. It is necessary to detect incipient faults to improve power grid security.
Xinlu Tang, Qiushi Cui, Yang Weng, Yuxiang Su, Dongdong Li   +4 more
doaj   +1 more source

Waveform to Single Sinusoid Regression to Estimate the F0 Contour from Noisy Speech Using Recurrent Deep Neural Networks

, 2018
The fundamental frequency (F0) represents pitch in speech that determines prosodic characteristics of speech and is needed in various tasks for speech analysis and synthesis. Despite decades of research on this topic, F0 estimation at low signal-to-noise
Kato, Akihiro, Kinnunen, Tomi
core   +1 more source

Electro‐Chemo‐Mechanical Coupling in Hf0.5Zr0.5O2 Ferroionic Heterostructures

Advanced Functional Materials, EarlyView.
Schematic of a ferroionic HZO heterostructure where epitaxial interfaces enable dynamic oxygen‐vacancy exchange, coupling ionic and ferroelectric degrees of freedom. Vacancy‐mediated polarization modulation biases HZO polymorphism, suppresses leakage, and enhances piezoelectric response, yielding distinct butterfly‐loop evolution and diode‐like ...
Achilles Bergne, Denis Alikin, Milica Vasiljevic, Victor B. Tinti, Javier Zamudio‐García, Leonardo Soares de Oliveira, Megan Landberg, Dimitrios Koukoulis, Huaiyu Chen, Jesper Wallentin, David Marrero‐López, Astri Bjørnetun Haugen, Sizhao Huang, Dennis Christensen, Nini Pryds, Alexander Tselev, Andrei Kholkin, Vincenzo Esposito   +17 more
wiley   +1 more source

High Linearity Synaptic Devices Using Ar Plasma Treatment on HfO₂ Thin Film with Non-Identical Pulse Waveforms

Nanomaterials, 2022
We enhanced the device uniformity for reliable memory performances by increasing the device surface roughness by exposing the HfO2 thin film surface to argon (Ar) plasma.
Ke-Jing Lee, Yu-Chuan Weng, Li-Wen Wang, Hsin-Ni Lin, Parthasarathi Pal, Sheng-Yuan Chu, Darsen Lu, Yeong-Her Wang   +7 more
doaj   +1 more source

Improved Speech Reconstruction from Silent Video

, 2017
Speechreading is the task of inferring phonetic information from visually observed articulatory facial movements, and is a notoriously difficult task for humans to perform.
Ephrat, Ariel, Halperin, Tavi, Peleg, Shmuel   +2 more
core   +1 more source

Optoelectronic Synaptic Devices Using Molecular Telluride Phase‐Change Inks for Three‐Factor Learning

Advanced Functional Materials, EarlyView.
Optoelectronic synaptic devices based on solution‐processed molecular telluride GST‐225 phase‐change inks are demonstrated for three‐factor learning. A global optical signal broadcast through a silicon waveguide induces non‐volatile conductance updates exclusively in locally electrically flagged memristors.
Kevin Portner, Dhananjeya Kumaar, Giacomo Torti, Killian Keller, Till Zellweger, Florian M. Schenk, Christoph Weilenmann, Daniel Chelladurai, Vara Prasad Jonnalagadda, Ghazi Sarwat Syed, Vanessa Wood, Jürg Leuthold, Alexandros Emboras, Maksym Yarema, Mathieu Luisier   +14 more
wiley   +1 more source

A Waveform-Feature Dual Branch Acoustic Embedding Network for Emotion Recognition

Frontiers in Computer Science, 2020
Research in advancing speech emotion recognition (SER) has attracted a lot of attention due to its critical role for better human behaviors understanding scientifically and comprehensive applications commercially.
Jeng-Lin Li, Jeng-Lin Li, Tzu-Yun Huang, Tzu-Yun Huang, Chun-Min Chang, Chun-Min Chang, Chi-Chun Lee, Chi-Chun Lee   +7 more
doaj   +1 more source