Research on music signal feature recognition and reproduction technology based on multilayer feedforward neural network
In this paper, a multi-layer feed-forward neural network is used to construct a Meier spectrogram recognition system. By analyzing the algorithmic role of recurrent neural, the backpropagation algorithm is applied to update the weights in the neural network to obtain the mapping relationship between...
| Main Author: | |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Sciendo
2024-01-01
|
| Series: | Applied Mathematics and Nonlinear Sciences |
| Subjects: | |
| Online Access: | https://doi.org/10.2478/amns.2023.2.00647 |
| _version_ | 1797340721522409472 |
|---|---|
| author | Li Huanzi |
| author_facet | Li Huanzi |
| author_sort | Li Huanzi |
| collection | DOAJ |
| description | In this paper, a multi-layer feed-forward neural network is used to construct a Meier spectrogram recognition system. By analyzing the algorithmic role of recurrent neural, the backpropagation algorithm is applied to update the weights in the neural network to obtain the mapping relationship between audio input and output. Combined with the algorithmic formula of the spectrum, the short-time Fourier transform is used to analyze the audio information. By architecting a multilayer feedforward recurrent neural network, the music signals are fused and classified. The cross-entropy loss function is applied to calculate the accuracy of micro and macro averages to improve the accuracy of music signal feature recognition. The results show that the feedforward recurrent neural network has the lowest error rate in different note recognition, and the error rate for “do” is 4%. |
| first_indexed | 2024-03-08T10:07:21Z |
| format | Article |
| id | doaj.art-0740ae4b21e447018c097f18389b7a84 |
| institution | Directory Open Access Journal |
| issn | 2444-8656 |
| language | English |
| last_indexed | 2024-03-08T10:07:21Z |
| publishDate | 2024-01-01 |
| publisher | Sciendo |
| record_format | Article |
| series | Applied Mathematics and Nonlinear Sciences |
| spelling | doaj.art-0740ae4b21e447018c097f18389b7a842024-01-29T08:52:34ZengSciendoApplied Mathematics and Nonlinear Sciences2444-86562024-01-019110.2478/amns.2023.2.00647Research on music signal feature recognition and reproduction technology based on multilayer feedforward neural networkLi Huanzi01College of Art and Design, Yantai Institute of Science and Technology, Yantai, Shandong, 265600, China.In this paper, a multi-layer feed-forward neural network is used to construct a Meier spectrogram recognition system. By analyzing the algorithmic role of recurrent neural, the backpropagation algorithm is applied to update the weights in the neural network to obtain the mapping relationship between audio input and output. Combined with the algorithmic formula of the spectrum, the short-time Fourier transform is used to analyze the audio information. By architecting a multilayer feedforward recurrent neural network, the music signals are fused and classified. The cross-entropy loss function is applied to calculate the accuracy of micro and macro averages to improve the accuracy of music signal feature recognition. The results show that the feedforward recurrent neural network has the lowest error rate in different note recognition, and the error rate for “do” is 4%.https://doi.org/10.2478/amns.2023.2.00647recurrent neuralloss functionback-propagation algorithmmel-spectrogram recognition00a65 |
| spellingShingle | Li Huanzi Research on music signal feature recognition and reproduction technology based on multilayer feedforward neural network Applied Mathematics and Nonlinear Sciences recurrent neural loss function back-propagation algorithm mel-spectrogram recognition 00a65 |
| title | Research on music signal feature recognition and reproduction technology based on multilayer feedforward neural network |
| title_full | Research on music signal feature recognition and reproduction technology based on multilayer feedforward neural network |
| title_fullStr | Research on music signal feature recognition and reproduction technology based on multilayer feedforward neural network |
| title_full_unstemmed | Research on music signal feature recognition and reproduction technology based on multilayer feedforward neural network |
| title_short | Research on music signal feature recognition and reproduction technology based on multilayer feedforward neural network |
| title_sort | research on music signal feature recognition and reproduction technology based on multilayer feedforward neural network |
| topic | recurrent neural loss function back-propagation algorithm mel-spectrogram recognition 00a65 |
| url | https://doi.org/10.2478/amns.2023.2.00647 |
| work_keys_str_mv | AT lihuanzi researchonmusicsignalfeaturerecognitionandreproductiontechnologybasedonmultilayerfeedforwardneuralnetwork |