Emotion Classification Algorithm for Audiovisual Scenes Based on Low-Frequency Signals
Since informatization and digitization came into life, audio signal emotion classification has been widely studied and discussed as a hot issue in many application fields. With the continuous development of artificial intelligence, in addition to speech and music audio signal emotion classification...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-06-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/13/12/7122 |
| _version_ | 1797596239468953600 |
|---|---|
| author | Peiyuan Jin Zhiwei Si Haibin Wan Xiangrui Xiong |
| author_facet | Peiyuan Jin Zhiwei Si Haibin Wan Xiangrui Xiong |
| author_sort | Peiyuan Jin |
| collection | DOAJ |
| description | Since informatization and digitization came into life, audio signal emotion classification has been widely studied and discussed as a hot issue in many application fields. With the continuous development of artificial intelligence, in addition to speech and music audio signal emotion classification technology, which is widely used in production life, its application is also becoming more and more abundant. Current research on audiovisual scene emotion classification mainly focuses on the frame-by-frame processing of video images to achieve the discrimination of emotion classification. However, those methods have the problems of algorithms with high complexity and high computing cost, making it difficult to meet the engineering needs of real-time online automatic classification. Therefore, this paper proposes an automatic algorithm for the detection of effective movie shock scenes that can be used for engineering applications by exploring the law of low-frequency sound effects on the perception of known emotions, based on a database of movie emotion scene clips in 5.1 sound format, extracting audio signal feature parameters and performing dichotomous classification of shock and other types of emotions. As LFS can enhance a sense of shock, a monaural algorithm for detecting emotional scenes with impact using a subwoofer (SW) is proposed, which trained a classification model using SW monaural features and achieved a maximum accuracy of 87% on the test set using a convolutional neural network (CNN) model. To expand the application scope of the above algorithm, a monaural algorithm for detecting emotional scenes with impact based on low-pass filtering (with a cutoff frequency of 120 Hz) is proposed, which achieved a maximum accuracy of 91.5% on the test set using a CNN model. |
| first_indexed | 2024-03-11T02:48:48Z |
| format | Article |
| id | doaj.art-78e4399568c64670bee49a6881373b2e |
| institution | Directory Open Access Journal |
| issn | 2076-3417 |
| language | English |
| last_indexed | 2024-03-11T02:48:48Z |
| publishDate | 2023-06-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj.art-78e4399568c64670bee49a6881373b2e2023-11-18T09:09:19ZengMDPI AGApplied Sciences2076-34172023-06-011312712210.3390/app13127122Emotion Classification Algorithm for Audiovisual Scenes Based on Low-Frequency SignalsPeiyuan Jin0Zhiwei Si1Haibin Wan2Xiangrui Xiong3School of Computer, Electronics and Information, Guangxi University, 100 Daxue Road, Nanning 530004, ChinaSchool of Computer, Electronics and Information, Guangxi Key Laboratory of Multimedia Communications and Network Technology, Guangxi University, Nanning 530004, ChinaSchool of Computer, Electronics and Information, Guangxi Key Laboratory of Multimedia Communications and Network Technology, Guangxi University, Nanning 530004, ChinaCollege of Electronics and Information Engineering, Beibu Gulf University, Qinzhou 535000, ChinaSince informatization and digitization came into life, audio signal emotion classification has been widely studied and discussed as a hot issue in many application fields. With the continuous development of artificial intelligence, in addition to speech and music audio signal emotion classification technology, which is widely used in production life, its application is also becoming more and more abundant. Current research on audiovisual scene emotion classification mainly focuses on the frame-by-frame processing of video images to achieve the discrimination of emotion classification. However, those methods have the problems of algorithms with high complexity and high computing cost, making it difficult to meet the engineering needs of real-time online automatic classification. Therefore, this paper proposes an automatic algorithm for the detection of effective movie shock scenes that can be used for engineering applications by exploring the law of low-frequency sound effects on the perception of known emotions, based on a database of movie emotion scene clips in 5.1 sound format, extracting audio signal feature parameters and performing dichotomous classification of shock and other types of emotions. As LFS can enhance a sense of shock, a monaural algorithm for detecting emotional scenes with impact using a subwoofer (SW) is proposed, which trained a classification model using SW monaural features and achieved a maximum accuracy of 87% on the test set using a convolutional neural network (CNN) model. To expand the application scope of the above algorithm, a monaural algorithm for detecting emotional scenes with impact based on low-pass filtering (with a cutoff frequency of 120 Hz) is proposed, which achieved a maximum accuracy of 91.5% on the test set using a CNN model.https://www.mdpi.com/2076-3417/13/12/7122low frequency soundbrain wave measurement5.1 sound formatsdeep learningmovie shock scene detection |
| spellingShingle | Peiyuan Jin Zhiwei Si Haibin Wan Xiangrui Xiong Emotion Classification Algorithm for Audiovisual Scenes Based on Low-Frequency Signals Applied Sciences low frequency sound brain wave measurement 5.1 sound formats deep learning movie shock scene detection |
| title | Emotion Classification Algorithm for Audiovisual Scenes Based on Low-Frequency Signals |
| title_full | Emotion Classification Algorithm for Audiovisual Scenes Based on Low-Frequency Signals |
| title_fullStr | Emotion Classification Algorithm for Audiovisual Scenes Based on Low-Frequency Signals |
| title_full_unstemmed | Emotion Classification Algorithm for Audiovisual Scenes Based on Low-Frequency Signals |
| title_short | Emotion Classification Algorithm for Audiovisual Scenes Based on Low-Frequency Signals |
| title_sort | emotion classification algorithm for audiovisual scenes based on low frequency signals |
| topic | low frequency sound brain wave measurement 5.1 sound formats deep learning movie shock scene detection |
| url | https://www.mdpi.com/2076-3417/13/12/7122 |
| work_keys_str_mv | AT peiyuanjin emotionclassificationalgorithmforaudiovisualscenesbasedonlowfrequencysignals AT zhiweisi emotionclassificationalgorithmforaudiovisualscenesbasedonlowfrequencysignals AT haibinwan emotionclassificationalgorithmforaudiovisualscenesbasedonlowfrequencysignals AT xiangruixiong emotionclassificationalgorithmforaudiovisualscenesbasedonlowfrequencysignals |