Results 81 to 90 of about 4,664 (261)

Lipid Nanoparticle Co‐Delivery of mRNA and a Small Molecule Drug for Oral Cancer Chemoimmunotherapy

Advanced Materials, EarlyView.
Co‐encapsulation of p53 mRNA and the small molecule ciclopirox within a lipid nanoparticle yields an all‐in‐one chemoimmunotherapy for oral squamous cell carcinoma. The platform engages caspase‐driven apoptosis in cancer cells while repolarizing tumor‐associated macrophages, achieving tumor reduction in both p53‐susceptible and p53‐resistant models and
Marshall S. Padilla, Jacqueline J. Li, Qunzhou Zhang, Korey Patwari, Shihong Shi, Hannah M. Yamagata, Ryann A. Joseph, Briyanna N. Hymms, Sridatta V. Teerdhala, Emily Fitzgerald, Ori Z. Chalom, Kushol Gupta, Mohamad‐Gabriel Alameh, Drew Weissman, Anh D. Le, Michael J. Mitchell   +15 more
wiley   +1 more source

Speaker Embeddings to Improve Tracking of Intermittent and Moving Speakers

2025 33rd European Signal Processing Conference (EUSIPCO)
33rd European Signal Processing Conference (EUSIPCO 2025), Sep 2025, Palerme (Italie ...
Iatariene, Taous, Cui, Can, Guérin, Alexandre, Serizel, Romain   +3 more
openaire   +4 more sources

A Geometrically Transient Platform for Bioelectronic Implants

Advanced Materials, EarlyView.
Minimally invasive bioelectronic implants often compromise performance for smaller sizes. To resolve this optimization dilemma, a wireless bioelectronic implant with a transient geometry is introduced (MiFi). The origami‐inspired device miniaturizes up to sixfold for syringe insertion and autonomously unfolds post‐implantation.
Selin Olenik, John D. Goodwin, Atharv Naik, Philip Coatsworth, Ioi Chit Cheung, Farbod Amirghasemi, Anies Sohi, Ehsan Abedi, Tayeb Tadlaoui, Maral P. S. Mousavi, Andriy S. Kozlov, Victoria Salem, Andrew S. Cowburn, Firat Guder   +13 more
wiley   +1 more source

Variants of LSTM cells for single-channel speaker-conditioned target speaker extraction

EURASIP Journal on Audio, Speech, and Music Processing
Speaker-conditioned target speaker extraction aims at estimating the target speaker from a mixture of speakers utilizing auxiliary information about the target speaker.
Ragini Sinha, Christian Rollwage, Simon Doclo   +2 more
doaj   +1 more source

Effect of Noises and GSM Codings on Pre-Trained Speaker Embedding Models in Forensic Voice Comparison

IEEE Access
Deep learning has witnessed extensive application within speaker verification (SV) in recent years, particularly in feature extraction or embedding features. This study delves into examining the impact of noise and Global System for Mobile Communications
Mohammed Hamzah Alsalihi, David Sztaho
doaj   +1 more source

Hybrid Amyloid–Boron Nitride Aerogels for Lightweight Sound Insulation

Advanced Materials, EarlyView.
Amyloid fibrils template the mild formation of boron nitride–rich hybrid aerogels with hierarchical porosity, enhanced BN‐like ordering, and fibril‐reinforced mechanics. These ultralight materials combine thermal stability with strong sound absorption and transmission loss, offering a sustainable bio‐assisted route toward lightweight acoustic shields ...
Mohammad Peydayesh, Andrin Lustgarten, Stefan Schoenwald, Enrico Boschi, My Hanh Bui, Ali Miserez, Felix Donat, Christoph R. Müller, Raffaele Mezzenga   +8 more
wiley   +1 more source

Comparison of Modern Deep Learning Models for Speaker Verification

Applied Sciences
This research presents an extensive comparative analysis of a selection of popular deep speaker embedding models, namely WavLM, TitaNet, ECAPA, and PyAnnote, applied in speaker verification tasks.
Vitalii Brydinskyi, Yuriy Khoma, Dmytro Sabodashko, Michal Podpora, Volodymyr Khoma, Alexander Konovalov, Maryna Kostiak   +6 more
doaj   +1 more source

Negotiating in a Foreign Land: Understanding the Curious Interactions Between Intracellular Mitochondria and Internalized Nanoparticles

Advanced Materials Interfaces, EarlyView.
Therapeutic nano‐drug delivery systems interact with cellular mitochondria in a multitude of ways. While the complexity of such interactions disrupts the mitochondrial electron transport chain and increases reactive oxygen species production, thereby contributing to nanoparticle toxicity, they also present unique theranostic opportunities in diseases ...
Sourav Bhattacharjee
wiley   +1 more source

Graph Learning Based Speaker Independent Speech Emotion Recognition

Advances in Electrical and Computer Engineering, 2014
In this paper, the algorithm based on graph learning and graph embedding framework, Speaker-Penalty Graph Learning (SPGL), is proposed in the research of speech emotion recognition to solve the problems caused by different speakers.
XU, X., HUANG, C., WU, C., WANG, Q., ZHAO, L.   +4 more
doaj   +1 more source

Unified Hypersphere Embedding for Speaker Recognition

CoRR, 2018
Incremental improvements in accuracy of Convolutional Neural Networks are usually achieved through use of deeper and more complex models trained on larger datasets. However, enlarging dataset and models increases the computation and storage costs and cannot be done indefinitely.
Mahdi Hajibabaei, Dengxin Dai
openaire   +2 more sources