A New Approach for Music Generation with LSTM and K-means Clustering Algorithm

Fatemeh Taheri¹ Hamed Gorji²

Abstract :
A model of music generation with AI needs to recall past details and ability to understand the musical structure. LSMT (Long-short term memory) is possibly the most advantageous type of neural networks and because of the loop in them allowing information to persist, is capable of keeping track of temporally distant events that indicate general music structure. This paper introduces an algorithmic approach by K-means clustering algorithm and LSTM (Long-short time memory) neural network for music generation and discusses its results. First, K-means algorithm for a dataset clustering as an audio processing to recognize the converge input dataset with the maximum similarity based on key audio features which represent a music piece, and LSTM a type of recurrent neural networks to generate a new music content based on the clustering results and music coding structures in MIDI files, combination of clustering method and LSTM performs well in composing music, specifically in range of classical piano music in this study. In fact, this new approach considered audio features and music structures together.

Keywords : music generation rnn lstm k means audio features

---

زبان مقاله : انگلیسی
محور مقاله : تکنولوژی
محل انتشار : کنفرانس بین المللی مهندسی و تکنولوژی - نروژ
آدرس وب سایت کنفرانس : icetconf.com
کد IOI مقاله : XBKC-EZHFA
لینک مستقیم مقاله : https://isnac.ir/XBKC-EZHFA
نمایش چکیده فارسی : https://isnac.ir/SA/XBKC-EZHFA

سایر مقالات ارائه دهنده

1. A New Approach for Music Generation with LSTM and K-means Clustering Algorithm
2. Music Genre Classification Using a Combination Model of LSTM and K-NN Algorithm

سایر مقالات محل انتشار

1. Factors Affecting Health with Emphasis on Health Care Economic Costs
2. الگوی رفتاری فرو رفت شمع های پیش ساخته به نسبت تعداد ضربات در مقایسه با مقاومت خاک
3. بازطراحی محلات مسکونی با تمسک بر تغییر الگوی سکونت (نمونه موردی: محله خرمشهر واقع در منطقه 8 مشهد)
4. A New Approach for Music Generation with LSTM and K-means Clustering Algorithm
5. Effect of Ozonation on Microbial Properties of Rice Flour
6. Measuring of phytochemical and antioxidant compounds and identification of main phenolic compound in Anarijeh plant(Froriepiasubpinnata) extract by RP-HPLC method
7. بهسازی بافت روستایی با رویکرد توریست پذیری و گردشگری روستایی (نمونه موردی: روستای توئیجن همدان)
8. A Model for Increasing Electronic Payment Tendency (EPT) using Gamification
9. Enhancement mechanical strength of epoxy nanocomposites by Tannic acid/graphene oxide
10. تاثير پوشش گياهي در صرفه جوئي مصرف انرژي ساختمان
11. تشخیص بیماری Amd با استفاده از منطق فازی
12. تشخیص میزان مدت بقای بیمارانی که به دلیل سرطان سینه تحت عمل جراحی قرار گرفته اند با استفاده از الگوریتم خوشه بندی فازی
13. شناسایی ژن های بدخیم در سرطان سینه با استفاده از طبقه بندی کننده تابع پایه شعاعی
14. Seismic Behavior of New Lateral Bracing Systems Called “OGrid” and “Nested” in Mid-rise Buildings
15. Seismic Performance Investigation on an Innovative Lateral Bracing System (OGrid) in Tall Buildings