音樂情感參數(shù)化系統(tǒng)的研究與實現(xiàn)
發(fā)布時間：2018-08-26 21:11
【摘要】：在當(dāng)今互聯(lián)網(wǎng)浪潮的推動下，數(shù)字音樂的數(shù)量出現(xiàn)了爆炸式的增長，急需高效的分類管理方法。近年來，國內(nèi)外學(xué)者針對音樂檢索展開了廣泛、深入的研究，但是未能取得廣泛的應(yīng)用，一方面，，音樂檢索是一個多學(xué)科交叉領(lǐng)域，研究難度大；另一方面，目前的眾多研究多以音樂流派和情感標簽作為分類目標，類似傳統(tǒng)的分類管理方式，存在局限性。因此，開展音樂檢索相關(guān)研究具有重要的研究價值。 針對目前基于情感的音樂檢索研究的不足，本文提出以參數(shù)來表示音樂情感強弱的方法，首先提取音樂情感特征，組成特征向量，然后利用fisher算法進行維數(shù)壓縮，再通過大量的音樂樣本對音樂情感參數(shù)化系統(tǒng)進行訓(xùn)練，最終得到節(jié)奏、音調(diào)和音色三個描述音樂情感強弱的參數(shù)。本文的研究成果主要有以下幾個方面： 首先，音樂情感特征的研究，通過實驗證明MFCC是一組非常重要的參數(shù)，它在很大程度上決定了音樂情感分類的正確率。對于MFCC特征維數(shù)的選取，實驗結(jié)果表明，13、14維是比較合理的。不同特征之前沒有相互排斥，而是相互補充，因此搭配使用不同的特征有助于提高總體的分類正確率。 其次，F(xiàn)isher和SVM兩種不同算法分類性能比較，在音樂情感類別很少的情況下，比如2個類別，兩者分類性能接近，為了方便分類器設(shè)計、節(jié)省計算資源，優(yōu)先選擇Fisher分類器；在類別很多的時候，為了保證分類正確率，應(yīng)該選擇SVM這一類基于機器學(xué)習(xí)理論分類器；當(dāng)類別特別多，起到關(guān)鍵作用的是音樂情感特征的選取，而不是分類器算法，應(yīng)該將研究重點放在這方面。 最后，音樂情感參數(shù)化系統(tǒng)的設(shè)計，本文以Marsyas音頻處理庫為基礎(chǔ)，搭建了基于數(shù)據(jù)流模型的系統(tǒng)框架，選擇了適當(dāng)?shù)那楦刑卣鹘M成特征向量，同時選擇Fisher算法作為分類器，使用大量的音樂樣本進行了系統(tǒng)訓(xùn)練，并對節(jié)奏、音調(diào)和音色三個參數(shù)進行參數(shù)歸一化處理，最終完成了音樂情感參數(shù)化系統(tǒng)的實現(xiàn)。 測試實驗結(jié)果表明，本文實現(xiàn)的系統(tǒng)能夠達到88%的識別正確率，基本滿足實際應(yīng)用需求，可以為相關(guān)的音樂管理軟件提供搜索引擎，促進音樂自動搜索技術(shù)的發(fā)展。
[Abstract]:The number of digital music has been increasing explosively under the impetus of the current Internet wave, and the efficient classification management method is urgently needed. In recent years, scholars at home and abroad have carried out extensive and in-depth research on music retrieval, but they have not been widely used. On the one hand, music retrieval is a multidisciplinary field, which is difficult to study; on the other hand, At present, many researches take music genre and emotion label as the classification target, similar to the traditional classification management, there are some limitations. Therefore, the development of music retrieval related research has an important research value. Aiming at the deficiency of the research on music retrieval based on emotion at present, this paper proposes a method to express the intensity of music emotion by parameter. Firstly, the feature vector of music emotion is extracted, then the dimension is compressed by fisher algorithm. Then through a large number of music samples to carry on the training to the music emotion parameterization system, finally obtains the rhythm, the tone and the timbre to describe the music emotion strong and weak parameter. The main research results of this paper are as follows: firstly, the research of music emotion characteristics proves that MFCC is a group of very important parameters, which determines the correct rate of music emotion classification to a great extent. For the selection of MFCC characteristic dimension, the experimental results show that 1314 dimension is reasonable. Different features are not mutually exclusive but complement each other before, so collocation of different features can improve the overall classification accuracy. Secondly, the classification performance of SVM and SVM are compared. In the case of few categories of music emotion, such as two categories, the classification performance is similar. In order to facilitate the design of classifier and save computing resources, Fisher classifier is chosen first. When there are many categories, in order to ensure the classification accuracy, we should choose SVM, which is based on machine learning theory classifier, and when there are many categories, it is the selection of music emotion feature, not the classifier algorithm that plays a key role. Research should be focused on this area. Finally, the design of the music emotion parameterization system, based on the Marsyas audio processing database, the system frame based on the data flow model is built, and the appropriate emotion features are selected as the feature vector, and the Fisher algorithm is chosen as the classifier. A large number of music samples are used for systematic training, and the parameters of rhythm, tone and tone color are normalized. Finally, the realization of music emotion parameterization system is completed. The test results show that the system can achieve 88% correct recognition rate, basically meet the practical needs, can provide a search engine for the related music management software, and promote the development of automatic music search technology.
【學(xué)位授予單位】：華南理工大學(xué)
【學(xué)位級別】：碩士
【學(xué)位授予年份】：2013
【分類號】：TN912.3
本文編號：2206168
[Abstract]:The number of digital music has been increasing explosively under the impetus of the current Internet wave, and the efficient classification management method is urgently needed. In recent years, scholars at home and abroad have carried out extensive and in-depth research on music retrieval, but they have not been widely used. On the one hand, music retrieval is a multidisciplinary field, which is difficult to study; on the other hand, At present, many researches take music genre and emotion label as the classification target, similar to the traditional classification management, there are some limitations. Therefore, the development of music retrieval related research has an important research value. Aiming at the deficiency of the research on music retrieval based on emotion at present, this paper proposes a method to express the intensity of music emotion by parameter. Firstly, the feature vector of music emotion is extracted, then the dimension is compressed by fisher algorithm. Then through a large number of music samples to carry on the training to the music emotion parameterization system, finally obtains the rhythm, the tone and the timbre to describe the music emotion strong and weak parameter. The main research results of this paper are as follows: firstly, the research of music emotion characteristics proves that MFCC is a group of very important parameters, which determines the correct rate of music emotion classification to a great extent. For the selection of MFCC characteristic dimension, the experimental results show that 1314 dimension is reasonable. Different features are not mutually exclusive but complement each other before, so collocation of different features can improve the overall classification accuracy. Secondly, the classification performance of SVM and SVM are compared. In the case of few categories of music emotion, such as two categories, the classification performance is similar. In order to facilitate the design of classifier and save computing resources, Fisher classifier is chosen first. When there are many categories, in order to ensure the classification accuracy, we should choose SVM, which is based on machine learning theory classifier, and when there are many categories, it is the selection of music emotion feature, not the classifier algorithm that plays a key role. Research should be focused on this area. Finally, the design of the music emotion parameterization system, based on the Marsyas audio processing database, the system frame based on the data flow model is built, and the appropriate emotion features are selected as the feature vector, and the Fisher algorithm is chosen as the classifier. A large number of music samples are used for systematic training, and the parameters of rhythm, tone and tone color are normalized. Finally, the realization of music emotion parameterization system is completed. The test results show that the system can achieve 88% correct recognition rate, basically meet the practical needs, can provide a search engine for the related music management software, and promote the development of automatic music search technology.
【學(xué)位授予單位】：華南理工大學(xué)
【學(xué)位級別】：碩士
【學(xué)位授予年份】：2013
【分類號】：TN912.3
【參考文獻】
相關(guān)期刊論文 前5條
1 張一彬;周杰;邊肇祺;張大鵬;;一種新的基于分類的音頻流分割方法[J];電子學(xué)報;2006年04期
2 張一彬;周杰;邊肇祺;;基于內(nèi)容的戲曲分類與分析[J];計算機工程;2006年12期
3 盧堅 ,陳毅松 ,孫正興 ,張福炎;語音/音樂自動分類中的特征分析[J];計算機輔助設(shè)計與圖形學(xué)學(xué)報;2002年03期
4 張一彬;周杰;邊肇祺;郭軍;;基于內(nèi)容的音頻與音樂分析綜述[J];計算機學(xué)報;2007年05期
5 吳忻生;徐凱春;戚其豐;高紅霞;;一種音樂情緒參數(shù)化的方法[J];應(yīng)用聲學(xué);2013年01期
本文編號：2206168
本文鏈接：http://sikaile.net/kejilunwen/sousuoyinqinglunwen/2206168.html
最近更新
教材專著
