Acoustic scattering AI for non-invasive object classifications: A case study on hair assessment

2025/06/17 by Long-Vu Hoang, Hoang, Long-Vu, Tuan M. Nguyen +3
Agricultural and Biological Sciences · Computer Science · #Audio and Speech Processing (eess.AS) #Computation and Language (cs.CL) #FOS: Computer and information sciences #FOS: Electrical engineering #Face recognition and analysis #Food Supply Chain Traceability #Generative Adversarial Networks and Image Synthesis #Sound (cs.SD) #electronic engineering #information engineering

paper · pdf · doi:10.48550/arxiv.2506.14148

openalex publication_date 2025/06/17 · openalex created_date 2025/10/18 · openalex updated_date 2026/07/28

Abstract

This paper presents a novel non-invasive object classification approach using acoustic scattering, demonstrated through a case study on hair assessment. When an incident wave interacts with an object, it generates a scattered acoustic field encoding structural and material properties. By emitting acoustic stimuli and capturing the scattered signals from head-with-hair-sample objects, we classify hair type and moisture using AI-driven, deep-learning-based sound classification. We benchmark comprehensive methods, including (i) fully supervised deep learning, (ii) embedding-based classification, (iii) supervised foundation model fine-tuning, and (iv) self-supervised model fine-tuning. Our best strategy achieves nearly 90% classification accuracy by fine-tuning all parameters of a self-supervised model. These results highlight acoustic scattering as a privacy-preserving, non-contact alternative to visual classification, opening huge potential for applications in various industries.

Citations

• Nes2Net: A Lightweight Nested Architecture for Foundation Model Driven Speech Anti-spoofing
• LP-MusicCaps: LLM-Based Pseudo Music Captioning
• Estimation of speaker age and height from speech signal using bi-encoder transformer mixture model
• A Fine-tuned Wav2vec 2.0/HuBERT Benchmark For Speech Emotion Recognition, Speaker Verification and Spoken Language Understanding
• HuBERT: Self-Supervised Speech Representation Learning by Masked\n Prediction of Hidden Units
• AST: Audio Spectrogram Transformer
• Transformers in Vision: A Survey
• fairseq S2T: Fast Speech-to-Text Modeling with fairseq
• wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representations
• CNN Architectures for Large-Scale Audio Classification

Related

• Prediction of Object Geometry from Acoustic Scattering Using Convolutional Neural Networks
• Point-based Acoustic Scattering for Interactive Sound Propagation via Surface Encoding
• A Generative deep learning approach for shape recognition of arbitrary objects from phaseless acoustic scattering data
• A Deep Learning Framework for Three Dimensional Shape Reconstruction from Phaseless Acoustic Scattering Far-field Data
• Acoustic scene classification using auditory datasets