Wider or Deeper Neural Network Architecture for Acoustic Scene Classification with Mismatched Recording Devices

2022-03-23 · Lam Pham, Khoa Dinh, Dat Ngo, Hieu Tang, Alexander Schindler

In this paper, we present a robust and low complexity system for Acoustic Scene Classification (ASC), the task of identifying the scene of an audio recording. We first construct an ASC baseline system in which a novel inception-residual-based network architecture is proposed to deal with the mismatched recording device issue. To further improve the performance but still satisfy the low complexity model, we apply two techniques: ensemble of multiple spectrograms and channel reduction on the ASC baseline system. By conducting extensive experiments on the benchmark DCASE 2020 Task 1A Development dataset, we achieve the best model performing an accuracy of 69.9% and a low complexity of 2.4M trainable parameters, which is competitive to the state-of-the-art ASC systems and potential for real-life applications on edge devices.

📄 PDF Abstract BibTeX arXiv:2203.12314

Code (0)

등록된 구현이 없습니다.

Tasks

Acoustic Scene Classification Scene Classification

Impact of Fully Connected Layers on Performance of Convolutional Neural Networks for Image Classification

2019-01-21 · S. H. Shabbeer Basha, Shiv Ram Dubey, Viswanath Pulabaigari, Snehasis Mukherjee

The Convolutional Neural Networks (CNNs), in domains like computer vision, mostly reduced the need for handcrafted features due to its ability to learn the problem-specific features from the raw input data. However, the …

General Classification image-classification Image Classification

Deeper or Wider: A Perspective from Optimal Generalization Error with Sobolev Loss

2024-01-31 · Yahong Yang, Juncai He

Constructing the architecture of a neural network is a challenging pursuit for the machine learning community, and the dilemma of whether to go deeper or wider remains a persistent question. This paper explores a compari…

Wide Attention Is The Way Forward For Transformers?

2022-10-02 · Jason Ross Brown, Yiren Zhao, Ilia Shumailov, Robert D Mullins

The Transformer is an extremely powerful and prominent deep learning architecture. In this work, we challenge the commonly held belief in deep learning that going deeper is better, and show an alternative design approach…

CPU text-classification Text Classification

Robust, General, and Low Complexity Acoustic Scene Classification Systems and An Effective Visualization for Presenting a Sound Scene Context

2022-10-16 · Lam Pham, Dusan Salovic, Anahid Jalali, Alexander Schindler 외

In this paper, we present a comprehensive analysis of Acoustic Scene Classification (ASC), the task of identifying the scene of an audio recording from its acoustic signature. In particular, we firstly propose an incepti…

Acoustic Scene Classification Scene Classification

CNNs-based Acoustic Scene Classification using Multi-Spectrogram Fusion and Label Expansions

2018-09-05 · Weiping Zheng, Zhenyao Mo, Xiaotao Xing, Gansen Zhao

Spectrograms have been widely used in Convolutional Neural Networks based schemes for acoustic scene classification, such as the STFT spectrogram and the MFCC spectrogram, etc. They have different time-frequency characte…

Acoustic Scene Classification Classification General Classification Scene Classification