Results 81 to 90 of about 460,856 (296)

The Speaker Identification Model for Air-Ground Communication Based on a Parallel Branch Architecture

Applied Sciences
This study addresses the challenges of complex noise and short speech in civil aviation air-ground communication scenarios and proposes a novel speaker identification model, Chrono-ECAPA-TDNN (CET).
Weijun Pan, Shenhao Chen, Yidi Wang, Sheng Chen, Xuan Wang   +4 more
doaj   +1 more source

Hydrogel‐Based Airway‐on‐Tube With Perfusable Endothelial Lumen and Outward Epithelialization

Advanced Materials, EarlyView.
A hydrogel‐based airway‐on‐tube platform featuring a perfusable endothelial lumen and outward epithelialization is presented. The system supports primary human bronchial epithelial and lung microvascular endothelial coculture under air‐liquid interface conditions.
Ali Doryab, Jack F. Murphy, Michael Bartolf‐Kopp, Jenny C‐C Hsin, Alice Chernaik, Frank McCaughan, Yan Yan Shery Huang, Tomasz Jungst, Jürgen Groll   +8 more
wiley   +1 more source

Speaker-turn aware diarization for speech-based cognitive assessments

Frontiers in Neuroscience
IntroductionSpeaker diarization is an essential preprocessing step for diagnosing cognitive impairments from speech-based Montreal cognitive assessments (MoCA).MethodsThis paper proposes three enhancements to the conventional speaker diarization methods ...
Sean Shensheng Xu, Xiaoquan Ke, Man-Wai Mak, Ka Ho Wong, Helen Meng, Timothy C. Y. Kwok, Jason Gu, Jian Zhang, Wei Tao, Chunqi Chang   +9 more
doaj   +1 more source

Descriptors to Dynamics: A Materials and Device Perspective on in‐Materio Physical Reservoir Computing for Neuromorphic Edge Intelligence

Advanced Materials, EarlyView.
Intrinsic material dynamics are harnessed as computational resources for neuromorphic in‐materio physical reservoir computing. Defects, ionic motion, interfaces, percolation, geometry, and biasing shape transient states that provide fading memory, nonlinearity, and high‐dimensional projection for simple readout. A descriptor‐to‐dynamics framework links
Kshitij RB Singh, Alif Syafiq Kamarol Zaman, Muzhen Xu, Yuki Usami, Saptarshi Das, Hirofumi Tanaka   +5 more
wiley   +1 more source

Breaking Bottlenecks in Solid Electrolyte Discovery With Large Artificial Intelligence Models

Advanced Materials, EarlyView.
Large AI models are presented as a route to break key bottlenecks in solid electrolyte discovery by linking materials databases, machine‐learning interatomic potentials, large language models, and autonomous experiments. This perspective highlights how AI can accelerate the identification of solid electrolytes with fast ion transport, stable interfaces,
Eric Jianfeng Cheng, Min Hong, Zhiquan Zeng, Chuanyu Liu, Qian Wang, Melissa Jane Meadowcroft, Vlad Badilita, Carlos Miguel Costa, Senentxu Lanceros‐Méndez, Ying Li, Chenyao Ma, Weibo Gong, Surendra Kumar Martha, Aloysius Soon, Piao Ma, Di Zhang, Teguh Ariyanto, Sudaryanto, Hiroshi Kakinuma, Jie Zhao, Jiayu Peng, Pengfei Ou, Jun Lu, Shin‐ichi Orimo, Hao Li   +24 more
wiley   +1 more source

Optimization of Cross-Resolution Speaker Verification Based on Octuplet Loss [PDF]

Jisuanji gongcheng
Speaker verification in voiceprint recognition plays a key role in real-life applications such as human-computer interaction, medical diagnosis, and online meetings.
NING Meiling, QI Jiayin
doaj   +1 more source

Learning Speaker Embedding with Momentum Contrast

CoRR, 2020
Speaker verification can be formulated as a representation learning task, where speaker-discriminative embeddings are extracted from utterances of variable lengths. Momentum Contrast (MoCo) is a recently proposed unsupervised representation learning framework, and has shown its effectiveness for learning good feature representation for downstream ...
Ke Ding, Xuanji He, Guanglu Wan
openaire   +3 more sources

Advances in Bio‐Integrated Edge Computing Systems for Smart and Connected Health

Advanced Materials, EarlyView.
This review explores advances in bio‐integrated edge computing for healthcare, focusing on co‐designing computing, sensing, and energy strategies to overcome integration and power challenges for optimized, decentralized operation. ABSTRACT Recent advances in bio‐integrated healthcare technologies have enabled continuous, high‐resolution monitoring and ...
Gyuwon Kim, Seungwon Yoo, Tae Woog Kang, Yunuo Huang, Woon‐Hong Yeo   +4 more
wiley   +1 more source

REAL-TIME JOINT ACOUSTIC ECHO CANCELLATION AND PERSONALIZED SPEECH ENHANCEMENT BASED ON CROSS-ATTENTION ALIGNMENT AND X- VECTOR [PDF]

ICTACT Journal on Communication Technology
Personalized speech enhancement (PSE) is a speech enhancement method to remove interfering speech, background noise, and reverberation based on a speaker embedding extracted from the target speaker such as d-vector and x-vector.
Kwon Kim, Yong-Hun Yun, Chol-Nam Om
doaj   +1 more source

Blending With Insulating Polymers Enables Stable Anti‐Ambipolar Characteristics in n‐Type Organic Mixed‐Conductors for Heterogeneous Spiking Neurons

Advanced Materials, EarlyView.
A polymer blend of n‐type OMIEC P(gNDI‐gT2) with insulating PMMA yields mechanically stabilized, anti‐ambipolar organic electrochemical transistors (OECTs) with tunable ionic‐electronic transport. This blending allows low‐power, fast‐spiking heterogeneous Hodgkin–Huxley neurons, enabling biomimetic frequency deconvolution and reservoir computing, which
Zachary Laswick, Ariel Lifer, Catherine Beaumont, Liad Hayoun, Priscila Cavassin, Zeinab Hamid, Dilara Meli, William Dupont, Lincoln J. Lauhon, Iain McCulloch, Gitti L. Frey, Giovanni Maria Matrone, Jonathan Rivnay   +12 more
wiley   +1 more source