Development of affective engine for lyrics retrieval toward listening context
Project/Area Number |
16K21482
|
Research Category |
Grant-in-Aid for Young Scientists (B)
|
Allocation Type | Multi-year Fund |
Research Field |
Multimedia database
Entertainment and game informatics 1
|
Research Institution | Kansai University (2020) Ritsumeikan University (2016-2019) |
Principal Investigator |
|
Project Period (FY) |
2016-04-01 – 2021-03-31
|
Project Status |
Completed (Fiscal Year 2020)
|
Budget Amount *help |
¥4,030,000 (Direct Cost: ¥3,100,000、Indirect Cost: ¥930,000)
Fiscal Year 2019: ¥1,040,000 (Direct Cost: ¥800,000、Indirect Cost: ¥240,000)
Fiscal Year 2018: ¥650,000 (Direct Cost: ¥500,000、Indirect Cost: ¥150,000)
Fiscal Year 2017: ¥1,040,000 (Direct Cost: ¥800,000、Indirect Cost: ¥240,000)
Fiscal Year 2016: ¥1,300,000 (Direct Cost: ¥1,000,000、Indirect Cost: ¥300,000)
|
Keywords | 歌詞検索 / 言語処理 / 音楽情報処理 / クロスドメイン検索 / コンテクストアウェア推薦 / 情報推薦 / 情報抽出 / 単語重要度 / 歌詞の検索 / 感性 / 歌詞 / 情報検索 / 感性情報学 / ソフトコンピューティング |
Outline of Final Research Achievements |
This research has developed an affective lyrics retrieval system complying with contextual queries focusing on linguistic aspect of music. Thorough the research, findings to cover characteristic features in lyrics and methods to analyze and represent the contextual queries have been revealed. Based on such achievement, a lyrics retrieval system complying with affection toward tourist spot has been developed as a typical application of lyrics retrieval. In the proposed system, the reviews have been assumed as pseudo lyrics as those were modeled by the word-embedding model which learned lyrics corpus. Moreover, as reviews and lyrics were pre-processed according to characteristic features of lyrics, the usability of the proposed system has been improved.
|
Academic Significance and Societal Importance of the Research Achievements |
本研究成果によって,音楽の言語的側面である歌詞についての言語的特徴が明らかになった.またコンテキスト分析に関わる基礎的な知見と技術を明らかにした.これらの知見や技術は歌詞の検索のみならず,英語教育やストーリー性をもったテキスト情報の分析にも応用可能である. 構築した歌詞検索システムのプロトタイプの評価では,異なるドメインの文書を横断的に検索するうえで,文書ドメインごとの特徴を明示的に取り入れることでの検索結果の有用性向上についての知見も得られた.
|
Report
(6 results)
Research Products
(25 results)