Research on Multimodal Generation Strategy of Opera Style and Music Melody Based on Time Series Analysis
Bibliographic record
Abstract
The application of artificial intelligence on the field of art can be used to assist the creation of musicians and provide new creative ideas for musicians.In this paper, firstly, an ARIMA model is established for the prediction problem of opera style, which is used to predict the trend of the development of opera style sequence, and the best model is selected according to the minimum information criterion and Bayesian criterion.Then an automatic music melody generation method based on the generative adversarial network framework is proposed, which applies the trained natural language generation model to music generation to textualize the music melody and reduce the model running time.In addition to this a barization music melody generation method is also used, which divides a large music melody into melodic segments and generates them segment by segment, reducing the difficulty of the model in generating the music melody.Finally, the Fourier transform method is used to extract the features of the music melody and complete the visualization of the music melody.The model ARIMA(2,1,1)(2,1,0)12 that best fits with the time-series prediction of the development of opera styles was identified through empirical analysis.The PB value of Leak-GAN_2 model in this paper is improved by 41.38% compared with MusicGAN.It shows that both the opera style prediction model and the music melody multimodal generation model constructed in this paper have better effect and certain advancement.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.002 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.001 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.001 |
| Open science | 0.001 | 0.000 |
| Research integrity | 0.000 | 0.001 |
| Insufficient payload (model declined to judge) | 0.002 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".