# Comparison of Time-Frequency Representations for Environmental Sound Classification using Convolutional Neural Networks

arXiv: https://arxiv.org/abs/1706.07156 · HTML: https://mlsanity.com/paper/1706.07156/

## Key facts

- Cited by 14 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 22 Jun 2017.

## Built on by (most cited first, 14 of 14)

- [Slow-Fast Auditory Streams For Audio Recognition](https://mlsanity.com/paper/2103.03516/) (2021)
- [CMKD: CNN/Transformer-Based Cross-Model Knowledge Distillation for Audio Classification](https://mlsanity.com/paper/2203.06760/) (2022)
- [Where Is My Training Bottleneck? Hidden Trade-Offs in Deep Learning Preprocessing Pipelines](https://mlsanity.com/paper/2202.08679/) (2022)
- [Multi-view Audio and Music Classification](https://mlsanity.com/paper/2103.02420/) (2021)
- [Learning Temporal Resolution in Spectrogram for Audio Classification](https://mlsanity.com/paper/2210.01719/) (2022)
- [Echo-Reconstruction: Audio-Augmented 3D Scene Reconstruction](https://mlsanity.com/paper/2110.02405/) (2021)
- [From Environmental Sound Representation to Robustness of 2D CNN Models Against Adversarial Attacks](https://mlsanity.com/paper/2204.07018/) (2022)
- [Developing a Multi-variate Prediction Model For COVID-19 From Crowd-sourced Respiratory Voice Data](https://mlsanity.com/paper/2402.07619/) (2024)
- [Self-Supervised Beat Tracking in Musical Signals with Polyphonic Contrastive Learning](https://mlsanity.com/paper/2201.01771/) (2022)
- [End-to-End Audio Strikes Back: Boosting Augmentations Towards An Efficient Audio Classification Network](https://mlsanity.com/paper/2204.11479/) (2022)
- [Deep Feature Learning for Medical Acoustics](https://mlsanity.com/paper/2208.03084/) (2022)
- [Acoustic Identification of Ae. aegypti Mosquitoes using Smartphone Apps and Residual Convolutional Neural Networks](https://mlsanity.com/paper/2306.10091/) (2023)
- [Neural-Enhanced Dynamic Range Compression Inversion: A Hybrid Approach for Restoring Audio Dynamics](https://mlsanity.com/paper/2411.04337/) (2024)
- [Missingness as Signal: Channel-Independent Spectrogram Learning for Clinical Time Series Prediction](https://mlsanity.com/paper/2607.02938/) (2026)

## Abstract (arXiv)

Recent successful applications of convolutional neural networks (CNNs) to audio classification and speech recognition have motivated the search for better input representations for more efficient training. Visual displays of an audio signal, through various time-frequency representations such as spectrograms offer a rich representation of the temporal and spectral structure of the original signal. In this letter, we compare various popular signal processing methods to obtain this representation, such as short-time Fourier transform (STFT) with linear and Mel scales, constant-Q transform (CQT) and continuous Wavelet transform (CWT), and assess their impact on the classification performance of two environmental sound datasets using CNNs. This study supports the hypothesis that time-frequency representations are valuable in learning useful features for sound classification. Moreover, the actual transformation used is shown to impact the classification accuracy, with Mel-scaled STFT outperforming the other discussed methods slightly and baseline MFCC features to a large degree. Additionally, we observe that the optimal window size during transformation is dependent on the characteristics of the audio signal and architecturally, 2D convolution yielded better results in most cases compared to 1D.