Abstract
Audio signal classification finds various applications in detecting and monitoring health conditions in healthcare. Convolutional neural networks (CNN) have produced state-of-the-art results in image classification and are being increasingly used in other tasks, including signal classification. However, audio signal classification using CNN presents various challenges. In image classification tasks, raw images of equal dimensions can be used as a direct input to CNN. Raw time-domain signals, on the other hand, can be of varying dimensions. In addition, the temporal signal often has to be transformed to frequency-domain to reveal unique spectral characteristics, therefore requiring signal transformation. In this work, we overview and benchmark various audio signal representation techniques for classification using CNN, including approaches that deal with signals of different lengths and combine multiple representations to improve the classification accuracy. Hence, this work surfaces important empirical evidence that may guide future works deploying CNN for audio signal classification purposes.
Highlights
Sensing technologies find applications in detecting and monitoring health conditions
The robustness of Convolutional neural network (CNN), and forgoing the need for complex feature engineering and extraction required by conventional methods [14,15,16], it was not long before CNN was adopted in audio signal classification tasks, achieving results superior to conventional techniques [17,18,19]
For the sound event dataset, to form the spectrogram, each signal is divided into 15 frames with a 50% overlap and discrete Fourier transform (DFT) is computed using 64 points
Summary
Sensing technologies find applications in detecting and monitoring health conditions. CNN in particular, were originally designed for large datasets, techniques such as data augmentation [7], transfer learning [8], and regularization [9] have allowed their extension to small datasets with encouraging results [10,11,12,13]. Due to such advancements, the robustness of CNN, and forgoing the need for complex feature engineering and extraction required by conventional methods [14,15,16], it was not long before CNN was adopted in audio signal classification tasks, achieving results superior to conventional techniques [17,18,19]. Unlike in image classification, where raw images can be used as a direct input to the CNN, audio signal classification using CNN presents several practical challenges
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
