Search
9 articles for “audio classification”
-
Acoustic Sensing for City Flow: Quasi-Supervised Recognition of Sirens and Traffic for Urban Mobility Intelligence
Abstract: This paper frames environmental audio as a mobility telemetry source, extending a benchmark urban-sound corpus with transportation-critical classes—ambulance, firetruck, police, and traffic—and training spectrogram-based models under a quasi-supervised regime to support real-time city operations; leveraging 10-fold protocols, class-weighted objectives, and audiospecific augmentations (time stretch, pitch shift, SpecAugment, PatchAugment), the system benchmarks multiple CNN backbones combined with self-supervised learning paradigms enable the extraction of rich, discriminative acoustic representations, achieving strong multi-class …
Published in Trends in Electrical Engineering · Vol. 16, Issue 1, 2025 · pp. 42–50 Read article
-
Advancements in AI-Driven Sound Spectrogram Analysis: From Deep Learning to Quantum and Neuromorphic Processing
Abstract: The rapid advancement of artificial intelligence (AI) has significantly reshaped the field of audio signal processing, with sound spectrogram analysis emerging as a central research focus. Spectrograms provide a rich time–frequency representation of audio signals, making them particularly suitable for data-driven learning approaches. This paper presents an in-depth and original review of modern AI-based techniques applied to spectrogram analysis, highlighting their growing impact across critical application areas such as healthcare …
Published in Journal of Multimedia Technology & Recent Advancements · Vol. 13, Issue 1, 2026 · pp. 01–06 Read article
-
Comparative Analysis of MCNN and RCNN for Speech Emotion Recognition Using Gender Information
Abstract: Speech emotion recognition is a speech processing task and a computer-based approach designed to identify and classify the emotions conveyed in audio signals. The aim of this system is to evaluate a speaker's emotional state, such as happiness, anger, sadness, or frustration, by analyzing their speech patterns, which include prosodic features like pitch, frequency, and rhythm. Speech emotion recognition is used in various real-life scenarios that include Customer Service, Healthcare, …
Published in Journal of Communication Engineering & Systems · Vol. 15, Issue 1, 2025 · pp. 1–10 Read article
-
Classifying Abnormalities in Heartbeat Sound
Abstract: Heartbeat sounds play a major role in the detection of various diseases such as heart disease, hyperthyroidism, and high blood pressure in their early stages. In the proposed method, various abnormal and healthy heartbeat audio signals are given as input and the features are extracted using MFCC (mel-frequency cepstral coefficients). Then, a deep learning approach is applied in which the MFCC audio signals are sent to the CNN (convolutional neural …
Published in Research & Reviews: A Journal of Embedded System & Applications · Vol. 12, Issue 1, 2024 · pp. 24–31 Read article
-
Avian Echoes: Convolutional Neural Network for Bird Vocalization Detection
Abstract: Bird species identification is a complex task within ornithology that demands advanced technological solutions. This research presents an approach leveraging Convolutional Neural Networks (CNNs) for bird species recognition based on identification of bird sound, each employing unique datasets and methodologies. The objective involves a two-stage identification process, beginning with the construction of an ideal dataset. The crucial step involves converting 1D audio waveforms to 2D spectrograms, enhancing CNNs' ability to …
Published in Journal of Aerospace Engineering & Technology · Vol. 14, Issue 2, 2024 · pp. 26–37 Read article
-
Fault Diagnosis of Air Compressor (AC) System using Local Mean Decomposition (LMD) and Logistic Regression (LR) Machine Learning Classifier
Abstract: This article presents a detailed and systematic procedure for performing fault diagnosis in an air compressor (AC) system by analyzing the audio signals generated during its operation. The analysis covers both normal (healthy) conditions and seven distinct types of faults, including bearing failure, flywheel malfunction, inlet valve leakage, outlet valve leakage, non-return valve failure, piston ring defect, and rider belt issues. To acquire the acoustic signals, the researchers utilized a …
Published in Journal of Polymer & Composites · Vol. 14, Issue 1, 2026 · pp. 416–427 Read article
-
Garbage Classifier Using Arduino
Abstract: In today's era, where prioritizing sustainable methods of waste disposal is crucial, a pioneering initiative titled "Garbage Collection using Arduino Nano " stands out as a revolutionary approach to refining the traditional, labor-intensive methods of household waste collection. Utilizing the Arduino Nano microcontroller, this project introduces a sophisticated waste management system equipped with diverse sensors and mechanisms. Through the automation of waste collection, this avant-garde system not only enhances efficiency …
Published in Journal of Mechatronics and Automation · Vol. 11, Issue 1, 2024 · pp. 18–23 Read article
-
Development of Polymer-Based Sensors for Speech Emotion Recognition
Abstract: Traditional SER research often utilizes microphones with polymer components like Diaphragms and Membranes. Within some microphone designs, polymer membranes which plays a crucial role in converting sound pressure into electrical signals. The paper highlights the application (speech emotion recognition) and have tried to find polymer-based sensors. This work further delves deeper, investigating the performance of the CatBoost algorithm for emotion recognition in voice assistants designed for Indian languages. The research …
Published in Journal of Polymer & Composites · Vol. 12, Issue 5, 2024 · pp. 268–274 Read article
-
Identifying and Blocking of Non-productive Calls in Emergency Call System Using Machine Learning and IVRS Integration
Abstract: The Dial 100 emergency reaction gadget handles over 1,000,000 calls every day, with over 95% being unproductive, such as blank, machine-generated, and spoofed calls. These futile calls waste resources and put off responses to actual emergencies. This look presents a comprehensive solution integrating advanced name evaluation, system learning, and an interactive voice response system (IVRS) to filter out and prevent these calls. Our technique starts with studying incoming calls to …
Published in Journal of Communication Engineering & Systems · Vol. 14, Issue 3, 2024 · pp. 20–28 Read article