Results 51 to 60 of about 2,773 (174)

DrLS: Distortion‐Resistant Lossless Steganography via Colour Depth Interpolation

CAAI Transactions on Intelligence Technology, EarlyView.
ABSTRACT The lossless data steganography is to hide a certain amount of information into a container image. Previous lossless steganography methods fail to strike a balance between capacity, imperceptibility, accuracy, and robustness, commonly vulnerable to distortion on container images.
Youmin Xu, Xuanyu Zhang, Xiandong Meng, Jian Zhang   +3 more
wiley   +1 more source

Efficient Masked Autoencoder for Birdsong Representation with Applications on Wild Bird Species Classification

Integrative Zoology, EarlyView.
Research on mosquito feeding preferences and the malaria parasites they transmit is essential for understanding the interactions between hosts, vectors, and parasites. In this study, vertebrate hosts were identified in 72 mosquitoes. Most blood meals (58.7%) came from birds, representing 25 species, while 40.0% came from mammals (13 species), and 1.3 ...
Qin Zhang, Shipeng Hu, Hengrui Wang, Jizheng Yi, Guoxiong Zhou, Xiangyu Shen, Weixiong Peng, Zhishu Xiao, Aibin Chen   +8 more
wiley   +1 more source

Respiratory Rate Estimation from Audio Using Object Detection with Learnable Spectrograms

Applied Sciences
Sound event detection models commonly rely on spectrogram representations of audio signals and recent approaches have adapted image-based object detection architectures to acoustic domains.
Bernhards Bertulis, Jevgenijs Telicko, Andris Jakovics   +2 more
doaj   +1 more source

Polarization Engineering in Vinylene‐Linked COFs Toward Efficient Neuromorphic Computing

Advanced Science, Volume 13, Issue 56, 9 October 2026.
A vinyl‐linked covalent organic framework (COF‐DIBPY) was synthesized on a conductive substrate for memristor applications. Redox reactions and bromide migration enable low‐voltage (0.5V) conductance switching with high analog on/off ratio (15.7). The device was further integrated into a speech emotion recognition system for acoustic simulation and ...
Hao Wang, Lei Zhao, Haoyuan Yao, Qiongshan Zhang, Fuzhen Xuan, Bin Zhang   +5 more
wiley   +1 more source

Mel-spectrogram augmentation for sequence to sequence voice conversion

CoRR, 2020
For training the sequence-to-sequence voice conversion model, we need to handle an issue of insufficient data about the number of speech pairs which consist of the same utterance. This study experimentally investigated the effects of Mel-spectrogram augmentation on training the sequence-to-sequence voice conversion (VC) model from scratch.
Hwang, Yeongtae, Cho, Hyemin, Yang, Hongsun, Won, Dong-Ok, Oh, Insoo, Lee, Seong-Whan   +5 more
openaire   +2 more sources

Hydrogen‐Stabilized Self‐Rectifying Memristor Arrays for Reliable Multilevel Synapses in Transformer‐Based Keyword Spotting

Advanced Science, Volume 13, Issue 56, 9 October 2026.
A non‐filamentary self‐rectifying HfO2/TiOx resistive random‐access memory integrates H2 annealing with an incremental step pulse with verify algorithm to achieve stable and linear analog conductance modulation. The device enables low‐current 6‐bit multilevel operation while suppressing sneak current in crossbar arrays. Implemented in Transformer‐based
Seonjeong Lee, Seohyeon Ju, Won Joo Lee, Myounggon Kang, Sungjun Kim, Yoon Kim   +5 more
wiley   +1 more source

Chilean Dolphins (Cephalorhynchus eutropia) Produce Both Narrowband High‐Frequency and Broadband Clicks

Marine Mammal Science, Volume 42, Issue 4, October 2026.
ABSTRACT Most dolphin species produce broadband biosonar clicks for echolocating prey, and whistles and burst‐pulsed calls for communication purposes. Seven dolphin species were previously reported to only produce clicks of a narrowband high‐frequency (NBHF) type, very similar to the clicks produced by porpoises.
Morgan J. Martin, Margherita Silvestri, Sara Torres Ortiz, Mauricio Soto‐Gamboa, Magnus Wahlberg, Frants H. Jensen   +5 more
wiley   +1 more source

Es-Tacotron2: Multi-Task Tacotron 2 with Pre-Trained Estimated Network for Reducing the Over-Smoothness Problem

Information, 2019
Text-to-speech synthesis is a computational technique for producing synthetic, human-like speech by a computer. In recent years, speech synthesis techniques have developed, and have been employed in many applications, such as automatic translation ...
Yifan Liu, Jin Zheng
doaj   +1 more source

Graph Embedding With Mel-Spectrograms for Underwater Acoustic Target Recognition

IEEE Journal of Oceanic Engineering
Underwater acoustic target recognition (UATR) is extremely challenging due to the complexity of ship-radiated noise and the variability of ocean environments. Although deep learning (DL) approaches have achieved promising results, most existing models implicitly assume that underwater acoustic data lie in a Euclidean space. This assumption, however, is
Sheng Feng, Shuqing Ma, Xiaoqian Zhu
openaire   +3 more sources

Delivery and Attitude Modulate Shared Neural Processing of Speech Through Distinct Frequency Channels

Psychophysiology, Volume 63, Issue 10, October 2026.
ABSTRACT Listeners' brains align when they attend to the same speech, but what determines how strongly they align is not well understood. We asked whether that alignment tracks the communicative relation between a listener and a message, manipulating it from the speaker's side and from the listener's, and bounding the account with a manipulation that ...
Barak Atia, Yair Berson, Abraham Goldstein   +2 more
wiley   +1 more source