講演抄録/キーワード |
講演名 |
2023-06-24 13:50
[ショートペーパー]SBERT-based Musical Components Estimation from Lyrics Trained with Imbalanced "Orpheus" Data ○Mastuti Puspitasari・Takuya Takahashi(UEC)・Gen Hori(AU)・Shigeki Sagayama・Toru Nakashika(UEC) SP2023-18 |
抄録 |
(和) |
(まだ登録されていません) |
(英) |
This research was done to develop neural models that are capable of estimating appropriate musical components based on lyrics input. We extracted paired data of lyrics and musical components from “Orpheus”, a Japanese automated composition system with over 6000 user-published songs on the platform and used them as training data. These lyrics are converted into text embeddings with Sentence-BERT and then fed into neural models with their respective musical components for training. The imbalance in the data is mitigated by using focal loss to avoid overfitting and the performance of our models are evaluated subjectively through a survey. These models can be implemented in automated composition system to provide automated setup recommendation for the users and or used as a source of
inspiration in conventional composition. |
キーワード |
(和) |
/ / / / / / / |
(英) |
Neural models / musical components / lyrics / Orpheus / automated composition / text embeddings / Sentence-BERT / focal loss |
文献情報 |
信学技報, vol. 123, no. 88, SP2023-18, pp. 86-90, 2023年6月. |
資料番号 |
SP2023-18 |
発行日 |
2023-06-16 (SP) |
ISSN |
Online edition: ISSN 2432-6380 |
著作権に ついて |
技術研究報告に掲載された論文の著作権は電子情報通信学会に帰属します.(許諾番号:10GA0019/12GB0052/13GB0056/17GB0034/18GB0034) |
PDFダウンロード |
SP2023-18 |