Fourier Hilbert: The input transformation to enhance CNN models for speech emotion recognition
Signal processing in general, and speech emotion recognition in particular, have long been familiar Artificial Intelligence (AI) tasks. With the explosion of deep learning, CNN models are used more frequently, accompanied by the emergence of many signal transformations. However, these methods often...
Saved in:
| Main Author: | |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
KeAi Communications Co. Ltd.
2024-01-01
|
| Series: | Cognitive Robotics |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2667241324000168 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850255640869470208 |
|---|---|
| author | Bao Long Ly |
| author_facet | Bao Long Ly |
| author_sort | Bao Long Ly |
| collection | DOAJ |
| description | Signal processing in general, and speech emotion recognition in particular, have long been familiar Artificial Intelligence (AI) tasks. With the explosion of deep learning, CNN models are used more frequently, accompanied by the emergence of many signal transformations. However, these methods often require significant hardware and runtime. In an effort to address these issues, we analyze and learn from existing transformations, leading us to propose a new method: Fourier Hilbert Transformation (FHT). In general, this method applies the Hilbert curve to Fourier images. The resulting images are small and dense, which is a shape well-suited to the CNN architecture. Additionally, the better distribution of information on the image allows the filters to fully utilize their power. These points support the argument that FHT provides an optimal input for CNN. Experiments conducted on popular datasets yielded promising results. FHT saves a large amount of hardware usage and runtime while maintaining high performance, even offers greater stability compared to existing methods. This opens up opportunities for deploying signal processing tasks on real-time systems with limited hardware. |
| format | Article |
| id | doaj-art-9e65b5fc189f4f8a918c02817453a658 |
| institution | OA Journals |
| issn | 2667-2413 |
| language | English |
| publishDate | 2024-01-01 |
| publisher | KeAi Communications Co. Ltd. |
| record_format | Article |
| series | Cognitive Robotics |
| spelling | doaj-art-9e65b5fc189f4f8a918c02817453a6582025-08-20T01:56:49ZengKeAi Communications Co. Ltd.Cognitive Robotics2667-24132024-01-01422823610.1016/j.cogr.2024.11.002Fourier Hilbert: The input transformation to enhance CNN models for speech emotion recognitionBao Long Ly0FPT University, Ho Chi Minh, Viet NamSignal processing in general, and speech emotion recognition in particular, have long been familiar Artificial Intelligence (AI) tasks. With the explosion of deep learning, CNN models are used more frequently, accompanied by the emergence of many signal transformations. However, these methods often require significant hardware and runtime. In an effort to address these issues, we analyze and learn from existing transformations, leading us to propose a new method: Fourier Hilbert Transformation (FHT). In general, this method applies the Hilbert curve to Fourier images. The resulting images are small and dense, which is a shape well-suited to the CNN architecture. Additionally, the better distribution of information on the image allows the filters to fully utilize their power. These points support the argument that FHT provides an optimal input for CNN. Experiments conducted on popular datasets yielded promising results. FHT saves a large amount of hardware usage and runtime while maintaining high performance, even offers greater stability compared to existing methods. This opens up opportunities for deploying signal processing tasks on real-time systems with limited hardware.http://www.sciencedirect.com/science/article/pii/S2667241324000168Speech emotion recognitionCNNInput transformationEnhancingFourier transformationHilbert curve |
| spellingShingle | Bao Long Ly Fourier Hilbert: The input transformation to enhance CNN models for speech emotion recognition Cognitive Robotics Speech emotion recognition CNN Input transformation Enhancing Fourier transformation Hilbert curve |
| title | Fourier Hilbert: The input transformation to enhance CNN models for speech emotion recognition |
| title_full | Fourier Hilbert: The input transformation to enhance CNN models for speech emotion recognition |
| title_fullStr | Fourier Hilbert: The input transformation to enhance CNN models for speech emotion recognition |
| title_full_unstemmed | Fourier Hilbert: The input transformation to enhance CNN models for speech emotion recognition |
| title_short | Fourier Hilbert: The input transformation to enhance CNN models for speech emotion recognition |
| title_sort | fourier hilbert the input transformation to enhance cnn models for speech emotion recognition |
| topic | Speech emotion recognition CNN Input transformation Enhancing Fourier transformation Hilbert curve |
| url | http://www.sciencedirect.com/science/article/pii/S2667241324000168 |
| work_keys_str_mv | AT baolongly fourierhilberttheinputtransformationtoenhancecnnmodelsforspeechemotionrecognition |