홈 › Papers

Data-Efficient Low-Complexity Acoustic Scene Classification in the DCASE 2024 Challenge

2024-05-16 · Florian Schmid, Paul Primus, Toni Heittola, Annamaria Mesaros, Irene Martín-Morató, Khaled Koutini, Gerhard Widmer

This article describes the Data-Efficient Low-Complexity Acoustic Scene Classification Task in the DCASE 2024 Challenge and the corresponding baseline system. The task setup is a continuation of previous editions (2022 and 2023), which focused on recording device mismatches and low-complexity constraints. This year's edition introduces an additional real-world problem: participants must develop data-efficient systems for five scenarios, which progressively limit the available training data. The provided baseline system is based on an efficient, factorized CNN architecture constructed from inverted residual blocks and uses Freq-MixStyle to tackle the device mismatch problem. The task received 37 submissions from 17 teams, with the large majority of systems outperforming the baseline. The top-ranked system's accuracy ranges from 54.3% on the smallest to 61.8% on the largest subset, corresponding to relative improvements of approximately 23% and 9% over the baseline system on the evaluation set.

📄 PDF Abstract BibTeX arXiv:2405.10018

Code (1)

CPJKU/dcase2024_task1_baseline 공식 구현 pytorch

Tasks

Acoustic Scene Classification Scene Classification

Acoustic scene classification in DCASE 2020 Challenge: generalization across devices and low complexity solutions

2020-05-29 · Toni Heittola, Annamaria Mesaros, Tuomas Virtanen

This paper presents the details of Task 1: Acoustic Scene Classification in the DCASE 2020 Challenge. The task consists of two subtasks: classification of data from multiple devices, requiring good generalization propert…

Acoustic Scene Classification Classification Scene Classification

Low-complexity CNNs for Acoustic Scene Classification

2022-08-02 · Arshdeep Singh, James A King, Xubo Liu, Wenwu Wang 외

This technical report describes the SurreyAudioTeam22s submission for DCASE 2022 ASC Task 1, Low-Complexity Acoustic Scene Classification (ASC). The task has two rules, (a) the ASC framework should have maximum 128K para…

Acoustic Scene Classification Classification Scene Classification

Low-Complexity Acoustic Scene Classification Using Parallel Attention-Convolution Network

2024-06-12 · Yanxiong Li, Jiaxin Tan, Guoqing Chen, Jialong Li 외

This work is an improved system that we submitted to task 1 of DCASE2023 challenge. We propose a method of low-complexity acoustic scene classification by a parallel attention-convolution network which consists of four m…

Acoustic Scene Classification Data Augmentation Knowledge Distillation Scene Classification

Low-Complexity Acoustic Scene Classification with Device Information in the DCASE 2025 Challenge

2025-05-03 · Florian Schmid, Paul Primus, Toni Heittola, Annamaria Mesaros 외

This paper presents the Low-Complexity Acoustic Scene Classification with Device Information Task of the DCASE 2025 Challenge and its baseline system. Continuing the focus on low-complexity models, data efficiency, and d…

Acoustic Scene Classification Scene Classification Transfer Learning

Low-complexity acoustic scene classification for multi-device audio: analysis of DCASE 2021 Challenge systems

2021-05-28 · Irene Martín-Morató, Toni Heittola, Annamaria Mesaros, Tuomas Virtanen

This paper presents the details of Task 1A Acoustic Scene Classification in the DCASE 2021 Challenge. The task targeted development of low-complexity solutions with good generalization properties. The provided baseline s…

Acoustic Scene Classification Quantization Scene Classification