Results 71 to 80 of about 10,198 (208)

Machine learning‐assisted vibrational detection and classification of drywood termite infestations

Approaches in Entomology: Methods, Philosophies, and Ethics, Volume 1, Issue 1, August‐December 2026.
Vibratory recordings combined with machine learning accurately detected drywood termite infestations within wood using a fully non‐destructive sensing approach. Models successfully classified termite presence and infestation intensity (empty, low, high density), achieving over 80% accuracy in both internal and external validation.
Lírio Cosme, Raul Narciso C. Guedes, Leonardo M. Turchen   +2 more
wiley   +1 more source

Implementation and Performance Analysis of Mel Frequency Cepstral Coefficient Features in Dangdut Music Sub-Genre Classification

Journal of Applied Informatics and Computing
This study investigates the classification of dangdut music sub-genres using Mel-Frequency Cepstral Coefficients (MFCC) and machine learning approaches.
I Nyoman Surya Jaya, Tria Hikmah Fratiwi, I Gede Harsemadi, I Dewa Made Dharma Putra Santika, Ni Putu Nanda Maharani, Putu Andiny Julia Putri Rapayana   +5 more
doaj   +1 more source

WS2 Optoelectronic Memristive Reservoir Enabling Ultra‐Low‐Power, Multi‐Task, and Environmentally Stable Neuromorphic Computing

Advanced Science, Volume 13, Issue 47, 24 August 2026.
WS2‐based in‐memory sensing reservoir computing integrates sensing, memory, and computation in one compact device. It achieves ∼94% N‐MNIST, ∼93% eye motion perception, and ∼89% speech recognition with ultra‐low energy (∼25.5 fJ/spike). The system shows stability at 95% humidity, endurance over 1.5M cycles, and supports synaptic plasticity, enabling ...
Dayanand Kumar, Hanrui Li, Divyanshu Divyanshu, Dhananjay D. Kumbhar, Manoj Kumar Rajbhar, Amit Singh, Abdul Momin Syed, Selma Amara, Gianluca Setti, Nazek El‐Atab   +9 more
wiley   +1 more source

Accuracy Comparison of Support Vector Machine, Random Forest, and K-Nearest Neighbors for Sundanese Speech Classification

JISA (Jurnal Informatika dan Sains)
To support the preservation of the Sundanese language, speech recognition systems based on machine learning canbe developed. This study aims to evaluate and compare the classification performance of Support Vector Machine, Random Forest, and K-Nearest ...
Laela Nur Rohmah, Abdul Halim Anshor, Wahyu Hadikristanto   +2 more
doaj   +1 more source

Speech Preprocessing Method Based on Transmission Wave and Fluid Theory

Engineering Reports, Volume 8, Issue 8, August 2026.
With the continuous development of social economy, voice audio has become one of the important ways of streaming media, and is widely used in many fields. However, it is very important for how to process speech. In view of this requirement and limitation, this paper introduces transmission wave and fluid theory, tries to comb the corresponding noise ...
Lixian Wu, Weiwei Lai, Li Bu, Zhaoxiong Guan, Guangcai Wu, Yinglong Zheng   +5 more
wiley   +1 more source

SPEAKER IDENTIFICATION SYSTEM USING AUDIO SIGNAL AND DEEP LEARNING METHOD [PDF]

Proceedings on Engineering Sciences
Automatic Speaker Identification (ASI) does not result in high accuracy, so it is essential to develop a highly accurate Speaker Identification (SI) system. Artificial Intelligence has shown remarkable improvement in the development of such systems using
Neelam Nehra , Pardeep Sangwan , Neelu Trivedi   +2 more
doaj   +1 more source

Weaving Intelligence: Thermally Drawn Multimaterial Fibers Toward AI‐Enabled Smart Textiles

Advanced Materials, Volume 38, Issue 40, 17 July 2026.
Thermally drawn multimaterial fibers are rapidly advancing as intelligent structural units for next‐generation smart textiles. Integrating multimaterial architectures with neuromorphic and spiking‐neural‐network principles enables fabrics that can sense, compute, and adapt autonomously.
Vuong Dinh Trung, Jiaxiang Yi, Hieu Nguyen‐Duc, Tien Nu Hoang Lo, Weili Zhao, Chaoqun Dong, Fabien Sorin, Baris Caglar, Lei Wei, Tung Nguyen‐Dang   +9 more
wiley   +1 more source

Scale-invariant MFCCs for speech/speaker recognition

TURKISH JOURNAL OF ELECTRICAL ENGINEERING & COMPUTER SCIENCES, 2019
The feature extraction process is a fundamental part of speech processing. Mel frequency cepstral coefficients (MFCCs) are the most commonly used feature types in the speech/speaker recognition literature. However, the MFCC framework may face numerical issues or dynamic range problems, which decreases their performance.
Tüfekci Z., Dişken G.
openaire   +2 more sources

Newborns' Language Discrimination May Not Reflect Sensitivity to Speech Rhythm: Evidence From Computational Modeling

Developmental Science, Volume 29, Issue 4, July 2026.
ABSTRACT Human newborns are able to discriminate between certain languages but not others. This ability has long been attributed to sensitivity to rhythm—the temporal regularities in speech of different languages. Here, we demonstrate through a series of computational simulations that this discrimination behavior can be achieved using no temporal ...
Ruolan Leslie Famularo, Ali Aboelata, Thomas Schatz, Naomi H. Feldman   +3 more
wiley   +1 more source

Inter‐Model Feature Fusion for Robust Low‐Resource Speech Recognition

Applied AI Letters, Volume 7, Issue 2, June 2026.
Our Self‐Supervised Feature Fusion (SSF‐FT) method enhances low‐resource speech recognition by adaptively combining features from self‐supervised models trained with Contrastive, Predictive, and Reconstruction objectives. This attention‐weighted ensemble delivers robust performance, particularly in acoustically challenging conditions, extending current
Ussen Kimanuka, Ciira wa Maina, Osman Büyük   +2 more
wiley   +1 more source