Benchmarking Audio Signal Representation Techniques for Classification with Convolutional Neural Networks
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. Howe...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-05-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/21/10/3434 |
| _version_ | 1797534065646108672 |
|---|---|
| author | Roneel V. Sharan Hao Xiong Shlomo Berkovsky |
| author_facet | Roneel V. Sharan Hao Xiong Shlomo Berkovsky |
| author_sort | Roneel V. Sharan |
| collection | DOAJ |
| description | 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. |
| first_indexed | 2024-03-10T11:24:21Z |
| format | Article |
| id | doaj.art-dc607b9d8c98434c904608fdc8007047 |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-03-10T11:24:21Z |
| publishDate | 2021-05-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-dc607b9d8c98434c904608fdc80070472023-11-21T19:48:27ZengMDPI AGSensors1424-82202021-05-012110343410.3390/s21103434Benchmarking Audio Signal Representation Techniques for Classification with Convolutional Neural NetworksRoneel V. Sharan0Hao Xiong1Shlomo Berkovsky2Australian Institute of Health Innovation, Macquarie University, Sydney, NSW 2109, AustraliaAustralian Institute of Health Innovation, Macquarie University, Sydney, NSW 2109, AustraliaAustralian Institute of Health Innovation, Macquarie University, Sydney, NSW 2109, AustraliaAudio 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.https://www.mdpi.com/1424-8220/21/10/3434convolutional neural networksfusioninterpolationmachine learningspectrogramtime-frequency image |
| spellingShingle | Roneel V. Sharan Hao Xiong Shlomo Berkovsky Benchmarking Audio Signal Representation Techniques for Classification with Convolutional Neural Networks Sensors convolutional neural networks fusion interpolation machine learning spectrogram time-frequency image |
| title | Benchmarking Audio Signal Representation Techniques for Classification with Convolutional Neural Networks |
| title_full | Benchmarking Audio Signal Representation Techniques for Classification with Convolutional Neural Networks |
| title_fullStr | Benchmarking Audio Signal Representation Techniques for Classification with Convolutional Neural Networks |
| title_full_unstemmed | Benchmarking Audio Signal Representation Techniques for Classification with Convolutional Neural Networks |
| title_short | Benchmarking Audio Signal Representation Techniques for Classification with Convolutional Neural Networks |
| title_sort | benchmarking audio signal representation techniques for classification with convolutional neural networks |
| topic | convolutional neural networks fusion interpolation machine learning spectrogram time-frequency image |
| url | https://www.mdpi.com/1424-8220/21/10/3434 |
| work_keys_str_mv | AT roneelvsharan benchmarkingaudiosignalrepresentationtechniquesforclassificationwithconvolutionalneuralnetworks AT haoxiong benchmarkingaudiosignalrepresentationtechniquesforclassificationwithconvolutionalneuralnetworks AT shlomoberkovsky benchmarkingaudiosignalrepresentationtechniquesforclassificationwithconvolutionalneuralnetworks |