Deep Space Separable Distillation for Lightweight Acoustic Scene Classification

2024-05-06 · ShuQi Ye, Yuan Tian

Acoustic scene classification (ASC) is highly important in the real world. Recently, deep learning-based methods have been widely employed for acoustic scene classification. However, these methods are currently not lightweight enough as well as their performance is not satisfactory. To solve these problems, we propose a deep space separable distillation network. Firstly, the network performs high-low frequency decomposition on the log-mel spectrogram, significantly reducing computational complexity while maintaining model performance. Secondly, we specially design three lightweight operators for ASC, including Separable Convolution (SC), Orthonormal Separable Convolution (OSC), and Separable Partial Convolution (SPC). These operators exhibit highly efficient feature extraction capabilities in acoustic scene classification tasks. The experimental results demonstrate that the proposed method achieves a performance gain of 9.8% compared to the currently popular deep learning methods, while also having smaller parameter count and computational complexity.

📄 PDF Abstract BibTeX arXiv:2405.03567

Code (0)

등록된 구현이 없습니다.

Tasks

Acoustic Scene Classification ClassificationDeep LearningScene Classification

Methods 이 논문이 사용한 방법론

Convolution A convolution is a type of matrix operation, consisting of a kernel, a small matrix of weights, that slides over input data performing element-wise multiplication with the…

Lightweight and Generalizable Acoustic Scene Representations via Contrastive Fine-Tuning and Distillation

2025-10-04 · Kuang Yuan, Yang Gao, Xilin Li, Xinhao Mei 외 arxiv

Acoustic scene classification (ASC) models on edge devices typically operate under fixed class assumptions, lacking the transferability needed for real-world applications that require adaptation to new or refined acousti…

Acoustic Scene Classification

Improving Acoustic Scene Classification in Low-Resource Conditions

2024-12-30 · Zhi Chen, Yun-Fei Shao, Yong Ma, Mingsheng Wei 외

Acoustic Scene Classification (ASC) identifies an environment based on an audio signal. This paper explores ASC in low-resource conditions and proposes a novel model, DS-FlexiNet, which combines depthwise separable convo…

Acoustic Scene Classification Classification Data Augmentation Knowledge Distillation+3

DOA Estimation with Lightweight Network on LLM-Aided Simulated Acoustic Scenes

2025-11-11 · Haowen Li, Zhengding Luo, Dongyuan Shi, Boxiang Wang 외 arxiv

Direction-of-Arrival (DOA) estimation is critical in spatial audio and acoustic signal processing, with wide-ranging applications in real-world. Most existing DOA models are trained on synthetic data by convolving clean …

Improving Acoustic Scene Classification with City Features

2025-03-21 · Yiqiang Cai, Yizhou Tan, Shengchen Li, Xi Shao 외

Acoustic scene recordings are often collected from a diverse range of cities. Most existing acoustic scene classification (ASC) approaches focus on identifying common acoustic scene patterns across cities to enhance gene…

Acoustic Scene Classification Classification Knowledge Distillation Scene Classification

Low-Complexity Acoustic Scene Classification Using Data Augmentation and Lightweight ResNet

2023-06-03 · Yanxiong Li, Wenchang Cao, Wei Xie, Qisheng Huang 외

We present a work on low-complexity acoustic scene classification (ASC) with multiple devices, namely the subtask A of Task 1 of the DCASE2021 challenge. This subtask focuses on classifying audio samples of multiple devi…

Acoustic Scene Classification Data Augmentation Model Compression Scene Classification