專利授權區國立清華大學國際產學營運總中心 Operations Center for Industry Collaboration

搜尋專利授權區

關鍵字

» 新增關鍵字

選單

專利授權區

專利授權區
專利名稱(中)	使用對抗生成網路與逆增強式學習法的自動作曲系統及方法
專利名稱(英)	System and method for automatically composing music using approaches of generative adversarial network and adversarial inverse reinforcement learning algorithm
專利家族	中華民國：I784434
專利權人	國立清華大學 100.00%
發明人	蘇豐文,澤威爾
技術領域	文化創意,資訊工程

專利摘要(中)
本發明主要揭示一種使用對抗生成網路與逆增強式學習法的自動作曲系統，其包括：一樂曲資料庫、一樂曲特徵萃取單元、一第一運算模組、一第二運算模組以及一第三運算模組。其中，所述樂曲特徵萃取單元對儲存於該樂曲資料庫之中的各個參考樂曲資料執行一特徵萃取處理，從而萃取出複數個樂曲特徵。特別地，所述第一運算模組執行具有雙軸式結構(Bi-axial architecture)的長短期記憶神經網路演算法。並且，該第二運算模組利用一逆增強式學習(AIRL)演算法對複數個樂曲特徵執行一第二運算，從而獲取至少一音符獎勵函數。因此，本發明所產生的樂曲具有悅耳且接近人類曲目的優點。

專利摘要(中)

本發明主要揭示一種使用對抗生成網路與逆增強式學習法的自動作曲系統，其包括：一樂曲資料庫、一樂曲特徵萃取單元、一第一運算模組、一第二運算模組以及一第三運算模組。其中，所述樂曲特徵萃取單元對儲存於該樂曲資料庫之中的各個參考樂曲資料執行一特徵萃取處理，從而萃取出複數個樂曲特徵。特別地，所述第一運算模組執行具有雙軸式結構(Bi-axial architecture)的長短期記憶神經網路演算法。並且，該第二運算模組利用一逆增強式學習(AIRL)演算法對複數個樂曲特徵執行一第二運算，從而獲取至少一音符獎勵函數。因此，本發明所產生的樂曲具有悅耳且接近人類曲目的優點。

專利摘要(英)
The present invention discloses a system and a method for automatically composing music using approaches of generative adversarial network and adversarial inverse reinforcement learning algorithm, comprising: a music feature extracting unit, a first operation module, a second operation module and a third operation module. The music feature extracting unit performs a feature extracting process on each of reference music data stored in the reference music database, thereby extracting a plurality of music features. Particularly, the first operation module performs a long and short-term memory (LSTM) neural network algorithm with bi-axial architecture. The second operation module uses an adversarial inverse reinforcement learning (AIRL) algorithm to perform a second operation on the plurality of music features, thereby obtaining at least one reward function. According to foregoing features of the present invention, the music generated by the system and method of the present invention are melodic and like the music composed by humans.

專利摘要(英)

The present invention discloses a system and a method for automatically composing music using approaches of generative adversarial network and adversarial inverse reinforcement learning algorithm, comprising: a music feature extracting unit, a first operation module, a second operation module and a third operation module. The music feature extracting unit performs a feature extracting process on each of reference music data stored in the reference music database, thereby extracting a plurality of music features. Particularly, the first operation module performs a long and short-term memory (LSTM) neural network algorithm with bi-axial architecture. The second operation module uses an adversarial inverse reinforcement learning (AIRL) algorithm to perform a second operation on the plurality of music features, thereby obtaining at least one reward function. According to foregoing features of the present invention, the music generated by the system and method of the present invention are melodic and like the music composed by humans.

聯絡資訊
承辦人姓名	李曉琪
承辦人電話	03-5715131 #31061
承辦人Email	hsiaochi@mx.nthu.edu.tw