Search for Articles:
Title / Keyword
Author / Affiliation / Email
Journal
Article Type
 
 
Advanced Search
 
Section
Special Issue
Volume
Issue
Number
Page
 
5.3
2.5
Journals
Applied Sciences
Special Issues
AI in Audio Analysis: Spectrogram-Based Recognition
applsci-logo
Submit to Special Issue Submit Abstract to Special Issue Review for Applied Sciences Propose a Special Issue

Journal Menu

► Journal Menu

Journal Browser

► Journal Browser
share announcement

AI in Audio Analysis: Spectrogram-Based Recognition

A special issue of Applied Sciences (ISSN 2076-3417). This special issue belongs to the section "Computing and Artificial Intelligence".

Deadline for manuscript submissions: 20 May 2025 | Viewed by 3260

Special Issue Editor

Prof. Dr. Ian McLoughlin

E-Mail Website
Guest Editor
Information Technology Cluster, Singapore Institute of Technology, Singapore 138683, Singapore
Interests: audio and speech AI; sound event detection; sound scene analysis; language identification; dialect identification; speech enhancement

Special Issue Information

Dear Colleagues,

The general field of machine hearing [1] involves algorithms capable of interpreting and extracting meaning from auditory information, similar to how humans recognize sounds, voices, environments, and activities from sound. This research field encompasses sound event detection and classification, auditory scene analysis, forensic audio analysis, medical diagnosis from sound, and more. It includes speech-related tasks such as language and dialect identification, speaker identification, and emotion recognition. Automatic and machine learning approaches, collectively classified as AI, have achieved remarkable performance gains in recent years by representing one-dimensional single-channel audio as a two-dimensional spectrogram [2], whether linear, logarithmic, mel-scaled, constant-Q, stacked filterbanks, or encoded in other ways. Adding a dimension has allowed researchers to unlock the considerable power of image-processing AI techniques and is now commonly used in systems such as the audio spectrum transformer (AST) [3].

In this Special Issue, we explore and extend the field of spectrogram-based recognition. High-quality original research papers are sought in areas including (but not limited to) the following:

  • Applications of spectrogram-based audio classification;
  • Audio spectrogram-based regression;
  • Spectrogram-like representations for deep learning;
  • Audio feature transformation of spectrograms;
  • Efficient spectrogram-based recognition;
  • Spectrograms in speech analysis, enhancement, and coding;
  • Anomaly detection from spectral representations;
  • Speech and medical applications of audio spectrogram analysis.

[1] Richard F. Lyon, “Machine hearing: An emerging field”, IEEE signal processing magazine 27 (5), 131-139.

[2] H. Zhang, I. McLoughlin and Y. Song, "Robust sound event recognition using convolutional neural networks," 2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2015, pp. 559-563, doi: 10.1109/ICASSP.2015.7178031.

[3] Gong, Yuan, Yu-An Chung, and James Glass. "Ast: Audio spectrogram transformer." arXiv preprint arXiv:2104.01778 (2021).

Prof. Dr. Ian McLoughlin
Guest Editor

Manuscript Submission Information

Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All submissions that pass pre-check are peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 100 words) can be sent to the Editorial Office for announcement on this website.

Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-blind peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Applied Sciences is an international peer-reviewed open access semimonthly journal published by MDPI.

Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 2400 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.

Keywords

  • sound event detection and classification
  • sound scene detection
  • acoustic scene analysis
  • machine hearing
  • spectrograms
  • spectral estimation
  • audio spectrum transformer
  • acoustic feature maps

Benefits of Publishing in a Special Issue

  • Ease of navigation: Grouping papers by topic helps scholars navigate broad scope journals more efficiently.
  • Greater discoverability: Special Issues support the reach and impact of scientific research. Articles in Special Issues are more discoverable and cited more frequently.
  • Expansion of research network: Special Issues facilitate connections among authors, fostering scientific collaborations.
  • External promotion: Articles in Special Issues are often promoted through the journal's social media, increasing their visibility.
  • e-Book format: Special Issues with more than 10 articles can be published as dedicated e-books, ensuring wide and rapid dissemination.

Further information on MDPI's Special Issue policies can be found here.

Published Papers (3 papers)

Download All Papers
Order results
Result details
Show export options expand_more Show export options expand_less
Select all
Export citation of selected articles as:

Research

13 pages, 8836 KiB  
Article
Detection of Abnormal Symptoms Using Acoustic-Spectrogram-Based Deep Learning
by Seong-Yoon Kim, Hyun-Min Lee, Chae-Young Lim and Hyun-Woo Kim
Appl. Sci. 2025, 15(9), 4679; https://doi.org/10.3390/app15094679 - 23 Apr 2025
Abstract
Acoustic data inherently contain a variety of information, including indicators of abnormal symptoms. In this study, we propose a method for detecting abnormal symptoms by converting acoustic data into spectrogram representations and applying a deep learning model. Spectrograms effectively capture the temporal and [...] Read more.
Acoustic data inherently contain a variety of information, including indicators of abnormal symptoms. In this study, we propose a method for detecting abnormal symptoms by converting acoustic data into spectrogram representations and applying a deep learning model. Spectrograms effectively capture the temporal and frequency characteristics of acoustic signals. In this work, we extract key features such as spectrograms, Mel-spectrograms, and MFCCs from raw acoustic data and use them as input for training a convolutional neural network. The proposed model is based on a custom ResNet architecture that incorporates Bottleneck Residual Blocks to improve training stability and computational efficiency. The experimental results show that the model trained with Mel-spectrogram data achieved the highest classification accuracy at 97.13%. The models trained with spectrogram and MFCC data achieved 95.22% and 93.78% accuracy, respectively. The superior performance of the Mel-spectrogram model is attributed to its ability to emphasize critical acoustic features through Mel-filter banks, which enhances learning performance. These findings demonstrate the effectiveness of spectrogram-based deep learning models in identifying latent patterns within acoustic data and detecting abnormal symptoms. Future research will focus on applying this approach to a wider range of acoustic domains and environments. The results of this study are expected to contribute to the development of disease surveillance systems by integrating acoustic data analysis with artificial intelligence techniques. Full article
(This article belongs to the Special Issue AI in Audio Analysis: Spectrogram-Based Recognition)
►▼ Show Figures

Figure 1

17 pages, 3902 KiB  
Article
Dual-Path Beat Tracking: Combining Temporal Convolutional Networks and Transformers in Parallel
by Nikhil Thapa and Joonwhoan Lee
Appl. Sci. 2024, 14(24), 11777; https://doi.org/10.3390/app142411777 - 17 Dec 2024
Viewed by 1010
Abstract
The Transformer, a deep learning architecture, has shown exceptional adaptability across fields, including music information retrieval (MIR). Transformers excel at capturing global, long-range dependencies in sequences, which is valuable for tracking rhythmic patterns over time. Temporal Convolutional Networks (TCNs), with their dilated convolutions, [...] Read more.
The Transformer, a deep learning architecture, has shown exceptional adaptability across fields, including music information retrieval (MIR). Transformers excel at capturing global, long-range dependencies in sequences, which is valuable for tracking rhythmic patterns over time. Temporal Convolutional Networks (TCNs), with their dilated convolutions, are effective at processing local, temporal patterns with reduced complexity. Combining these complementary characteristics, global sequence modeling from Transformers and local temporal detail from TCNs enhances beat tracking while reducing the model’s overall complexity. To capture beat intervals of varying lengths and ensure optimal alignment of beat predictions, the model employs a Dynamic Bayesian Network (DBN), followed by Viterbi decoding for effective post-processing. This system is evaluated across diverse public datasets spanning various music genres and styles, achieving performance on par with current state-of-the-art methods yet with fewer trainable parameters. Additionally, we also explore the interpretability of the model using Grad-CAM to visualize the model’s learned features, offering insights into how the TCN-Transformer hybrid captures rhythmic patterns in the data. Full article
(This article belongs to the Special Issue AI in Audio Analysis: Spectrogram-Based Recognition)
►▼ Show Figures

Figure 1

16 pages, 10466 KiB  
Article
Hierarchical Residual Attention Network for Musical Instrument Recognition Using Scaled Multi-Spectrogram
by Rujia Chen, Akbar Ghobakhlou and Ajit Narayanan
Appl. Sci. 2024, 14(23), 10837; https://doi.org/10.3390/app142310837 - 22 Nov 2024
Cited by 1 | Viewed by 1023
Abstract
Musical instrument recognition is a relatively unexplored area of machine learning due to the need to analyze complex spatial–temporal audio features. Traditional methods using individual spectrograms, like STFT, Log-Mel, and MFCC, often miss the full range of features. Here, we propose a hierarchical [...] Read more.
Musical instrument recognition is a relatively unexplored area of machine learning due to the need to analyze complex spatial–temporal audio features. Traditional methods using individual spectrograms, like STFT, Log-Mel, and MFCC, often miss the full range of features. Here, we propose a hierarchical residual attention network using a scaled combination of multiple spectrograms, including STFT, Log-Mel, MFCC, and CST features (Chroma, Spectral contrast, and Tonnetz), to create a comprehensive sound representation. This model enhances the focus on relevant spectrogram parts through attention mechanisms. Experimental results with the OpenMIC-2018 dataset show significant improvement in classification accuracy, especially with the “Magnified 1/4 Size” configuration. Future work will optimize CST feature scaling, explore advanced attention mechanisms, and apply the model to other audio tasks to assess its generalizability. Full article
(This article belongs to the Special Issue AI in Audio Analysis: Spectrogram-Based Recognition)
►▼ Show Figures

Figure 1

Show export options expand_more Show export options expand_less
Select all
Export citation of selected articles as:
 
Displaying articles 1-3
Back to TopTop