【摘要】：音樂(lè)分類(lèi)從本質(zhì)上講是一個(gè)模式識(shí)別的問(wèn)題,主要包括兩個(gè)方面內(nèi)容：特征提取和分類(lèi)。一般音頻數(shù)據(jù)具有的高冗余、高維度的特點(diǎn),必須經(jīng)過(guò)特征提取才能有效的降低信號(hào)冗余度和維度。特征提取是通過(guò)對(duì)音頻信號(hào)進(jìn)行分析來(lái)獲得表征聲學(xué)信號(hào)隨時(shí)間變化的一組特征參數(shù)。不同的特征提取方法所提取的特征參數(shù)直接影響著后續(xù)音樂(lè)分類(lèi)的效果,是音樂(lè)分類(lèi)任務(wù)的關(guān)鍵步驟。深度學(xué)習(xí)作為一種新的特征提取技術(shù),在語(yǔ)音信號(hào)處理領(lǐng)域取得了一系列成功。本文借鑒深度學(xué)習(xí)在語(yǔ)音信號(hào)處理上的研究成果在音樂(lè)分類(lèi)與深度學(xué)習(xí)理論相結(jié)合的基礎(chǔ)上,針對(duì)如何利用深度學(xué)習(xí)強(qiáng)大的特征提取功能發(fā)現(xiàn)更加適用于音樂(lè)分類(lèi)的聲學(xué)特征這一問(wèn)題展開(kāi)研究。本文首先對(duì)音樂(lè)信息檢索的概念和常用方法進(jìn)行了介紹,接著介紹了深度學(xué)習(xí)原理以及典型模型。然后針對(duì)如何利用深度神經(jīng)網(wǎng)絡(luò)進(jìn)行音樂(lè)信息檢索問(wèn)題展開(kāi)研究。本文提出了一種利用深度信念網(wǎng)絡(luò)對(duì)音樂(lè)進(jìn)行情緒分類(lèi)算法,結(jié)合卷積神經(jīng)網(wǎng)絡(luò)提出了加入卷積操作的深度信念網(wǎng)絡(luò)。試驗(yàn)中,將用深度信念網(wǎng)絡(luò)提取到的特征與MFCC特征進(jìn)行比較,證明前者在音樂(lè)情緒分類(lèi)任務(wù)中能取得更好的效果。
[Abstract]:Music classification is essentially a problem of pattern recognition, which includes two aspects: feature extraction and classification. General audio data has the characteristics of high redundancy and high dimension, which must be extracted to effectively reduce the signal redundancy and dimension. Feature extraction is based on the analysis of audio signals to obtain a set of feature parameters that represent the variation of acoustic signals over time. The feature parameters extracted by different feature extraction methods directly affect the effect of the subsequent music classification and are the key steps of the music classification task. As a new feature extraction technique, depth learning has achieved a series of successes in the field of speech signal processing. On the basis of the combination of music classification and depth learning theory, this paper draws lessons from the research results of deep learning in speech signal processing. This paper focuses on how to use the powerful feature extraction function of depth learning to find acoustic features which are more suitable for music classification. This paper first introduces the concept and common methods of music information retrieval, then introduces the principle of deep learning and typical models. Then the research on how to use depth neural network for music information retrieval is carried out. In this paper, a deep belief network is proposed to classify music emotions, and a deep belief network with convolution neural network is proposed. In the experiment, the features extracted by the deep belief network are compared with the MFCC features, and it is proved that the former can achieve better results in the task of music emotion classification.
【學(xué)位授予單位】：北京郵電大學(xué)
【學(xué)位級(jí)別】：碩士
【學(xué)位授予年份】：2015
【分類(lèi)號(hào)】：TN912.3;TP183

【參考文獻(xiàn)】

相關(guān)期刊論文 前1條

1 余凱;賈磊;陳雨強(qiáng);徐偉;;深度學(xué)習(xí)的昨天、今天和明天[J];計(jì)算機(jī)研究與發(fā)展;2013年09期

，

本文編號(hào)：2218309