analiza aiqbench
This research introduces RALCT, a lightweight Convolutional Transformer architecture designed for environment sound recognition to enhance safety for the hearing impaired. By integrating CNNs with randomized audio augmentations and spectrogram features, the model achieves state-of-the-art accuracy on the UrbanSound8K dataset while remaining small enough for mobile deployment. The work represents a significant advancement in applying deep learning models to assistive technology beyond traditional speech processing.
"What's That Sound?": A Versatile, Robust, and Lightweight Convolutional Transformer for Environment Sound Recognition
arXiv:2609.27762v1 Announce Type: cross Abstract: The conventional hearing aid is both costly and lim- ited in usage, as it is not intended to detect non-speech audio. Our objective is to develop a machine learning solution to provide a more accurate and affordable mechanism to identify surrounding sounds to improve the safety of the hearing impaired, i.e., if a car is honking behind pedestrians, or a gunshot is fired, and they need to move away from the source. By adding randomized augmentations to audio, concatenating a Mel-Frequency Cepstral Coefficients (MFCCs) diagram and a log-mel Spectrogram, and including Convolutional Neural Networks (CNNs) in a Trans- former architecture, the Randomized Audiomentational Layered Convolutional Transformers (RALCT) model efficiently extracts features from diversified audio representations. In addition, RALCT is small enough, with only approximately 310,000 parameters, to be deployed into mobile devices. Experimental results on the UrbanSound8K dataset resulted in an accuracy consistently over 93% for all variations of RALCT with the highest at 94.56%, reaching state-of-the-art levels. To leverage the capabilities of this technology, a mobile app is developed to be integrated with the model to provide real-time safety control. RALCT thus represents a robust, lightweight, affordable, and versatile deep learning tool to aid the navigation and safety of the hearing impaired.
Title:"What's That Sound?": A Versatile, Robust, and Lightweight Convolutional Transformer for Environment Sound Recognition
Abstract:The conventional hearing aid is both costly and lim- ited in usage, as it is not intended to detect non-speech audio. Our objective is to develop a machine learning solution to provide a more accurate and affordable mechanism to identify surrounding sounds to improve the safety of the hearing impaired, i.e., if a car is honking behind pedestrians, or a gunshot is fired, and they need to move away from the source. By adding randomized augmentations to audio, concatenating a Mel-Frequency Cepstral Coefficients (MFCCs) diagram and a log-mel Spectrogram, and including Convolutional Neural Networks (CNNs) in a Trans- former architecture, the Randomized Audiomentational Layered Convolutional Transformers (RALCT) model efficiently extracts features from diversified audio representations. In addition, RALCT is small enough, with only approximately 310,000 parameters, to be deployed into mobile devices. Experimental results on the UrbanSound8K dataset resulted in an accuracy consistently over 93% for all variations of RALCT with the highest at 94.56%, reaching state-of-the-art levels. To leverage the capabilities of this technology, a mobile app is developed to be integrated with the model to provide real-time safety control. RALCT thus represents a robust, lightweight, affordable, and versatile deep learning tool to aid the navigation and safety of the hearing impaired.
Sound (cs.SD); Machine Learning (cs.LG)
I.2.6; I.5.4; H.5.5
arXiv:2609.27762 [cs.SD]
(or arXiv:2609.27762v1 [cs.SD] for this version)
https://doi.org/10.48550/arXiv.2609.27762 Focus to learn more arXiv-issued DOI via DataCite (pending registration)
https://doi.org/10.34614/2022IYRC21 Focus to learn more DOI(s) linking to related resources
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Text integral sub licența deschisă a publicației · 326 cuvinte
Subiecte conexe
Backpropagation-Free Test-Time Adaptation for Lightweight EEG-Based Brain-Computer Interfaces
arXiv · 24 iul. 2026
Together AI brings Thinking Machines Lab’s new model Inkling on day 0
Together AI · 15 iul. 2026
Robust Lightweight Deep Learning Models for Oral Cancer Screening
arXiv · 25 aug. 2026
Towards Robust Arabic Speech Emotion Recognition with Deep Learning
arXiv · 10 iun. 2026