改进音高轮廓创建和选择的旋律提取算法

针对复调音乐中不同声源的相互干扰而导致同一声源音高序列的不连续,从而降低音高估计精度的问题,提出改进音高轮廓创建和选择的旋律提取算法。算法首先计算时频谱中每一点的音高显著性,并提出基于听觉流线索和音高显著性的连续性创建音高轮廓;为了进一步选择旋律音高轮廓,随后提出根据伴奏的重复特性去除非旋律音高轮廓,主要采用动态时间规整算法计算旋律和非旋律音高轮廓间的相似度;最后,提出利用相邻音高轮廓的长时关系检测旋律音高轮廓中的倍频错误,并平滑旋律音高轮廓形成旋律音高线。在数据集ORCHSET上进行仿真实验,结果表明所提出的改进算法比改进前提高了2.86%的音高估计精度和3.32%的总精度,可有效解决音高估计问题。     

哼唱检索中一种新颖的基音周期提取算法

在哼唱检索（QBH）研究中,针对乐曲旋律表达方式以及有效的检索匹配算法已有一定的研究成果,但提取哼唱音频信息基音周期的算法研究还不充分。正确提取基音周期,降低哼唱信号基音周期提取过程中引入的误差,是有效提高整个检索性能的关键所在。在充分分析已有的基音周期提取方法基础上,提出了一种短时自相关（ACF）与短时平均幅度差（AMDF）函数相结合的CAA算法,仿真实验证明了新方法的有效性,相对于传统时域算法提取基音周期,准确度有显著提高。     

基于音乐旋律轮廓的特征提取算法

提出了一种基于音乐旋律轮廓的特征提取算法。该算法从哼唱片断中提取出歌曲基音序列,经规整、合并、分段后转化为旋律轮廓序列,然后使用标准音调生成的标准音调差值表将此序列转化为旋律轮廓特征。结果表明,该系统对环境噪声有较好的鲁棒性;在含有405首歌曲的搜索空间中,检索前5位成功率超过90%。     

Pitch estimation of speech and music sound based on multi-scale product with auditory feature extraction

The pitch is a crucial parameter in speech and music signals. However, due to severe noisy conditions, missing harmonics, unsuitable physical vibration, the determination of pitch presents a great challenge when desiring to get a good accuracy. In this paper, we propose a method for pitch estimation of speech and music sounds. Our method is based on the fast Fourier transform (FFT) of the multi-scale product (MP) provided by a feature auditory model of the sound signals. The auditory model simulates the spectral behaviour of the cochlea by a gammachirp filter-bank, and the out/middle ear filtering by a low-pass filter. For the two output channels, the FFT function of the MP is computed over frames. The MP is based on constituting the product of the speech and music wavelet transform coefficients at three scales. The experimental results show that our method estimates the pitch with high accuracy. Besides, our proposed method outperforms several other pitch detection algorithms in clean and noisy environments.     

改进的音高识别算法

提出了一种基于自相关处理和快速傅里叶变换（FFT）的改进的单音音高识别算法。利用修正的三电平中心削波函数对音乐信号进行预处理,再自相关处理估计基音周期,以估计周期为参数设计滤波器,音乐信号滤波后用FFT实现频域的准确定位。该算法比传统的时域处理法具有更高的识别精度,能比谐波峰值法更有效地解决谐波丰富、基频分量小的信号的识别,且运算量比小波算法小。经实验仿真验证该方法可行、快速可靠。     

基于相干小波变换的信号相位差估计

精确地估计两列信号间的传输延迟在工程上有着重要的意义。傅里叶变换方法很难区分或识别信号的瞬时变化,而小波变换方法是一种时间窗和频率窗都可改变的时频局部化的分析方法,在非平稳信号的分析方面具有明显的优势。给出应用Morlet小波变换的相干性实现两信号相位差估计的算法,在不同信噪比条件下,对算法的估计性能进行了仿真研究。仿真研究结果表明,在低信噪比的条件下,基于小波变换的相位差估计方法可以实现信号相位差的精确估计。通过与基于离散时间傅里叶变换方法的比较,验证了小波变换方法在估计信号相位差方面的优越性。该方法还可用于对非平稳信号相位差的估计。     

一种改进的基于音高显著性的旋律提取算法

针对复调音乐中不同声源的相互干扰导致的同一声源音高序列不连续，利用音高显著性的连续性和高次谐波的稳定性，提出基于音高静态似然性函数和音高显著性动态似然函数的创建音高轮廓方法；在提取旋律音高轮廓之前，为了利用不同声源音色的不一致性，提出计算音高轮廓的梅尔频率倒谱系数作为音色特征以及从音高轮廓的各次谐波幅度中计算音色特征。改进算法在RECHSET音乐数据集上进行仿真实验，结果表明达到了62.04%的音高估计精度和55.08%的总精度。     

一种基于隐马尔科夫模型的波形文件主旋律基频提取算法

哼唱检索中通常以旋律的基频作为音乐特征进行检索,目前研究的哼唱检索系统都是基于MIDI音乐文件。但是,目前存在的MIDI音乐文件的数量非常少,基于波形文件的哼唱检索系统才是未来的发展趋势。本文针对单声道波形文件,研究了一种提取歌曲主旋律基频曲线的算法。该算法将隐马尔科夫模型和“谐波乐器/打击乐器声音分离”模型进行结合。实验表明该算法对主旋律基频提取具有很高的准确率。     

基于音高旋律元的柔和乐曲的自动作曲算法

提出了一种以柔和为导向、以音高旋律元 (Pitch melody unit, PMU)为基本操作单位的自动作曲算法.首先根据柔和乐曲的旋律特征构建了算法的 规则模型.然后定义了一阶音高旋律元和二阶音高旋律元,构建了音高旋律元转换表 (Pitch melody unit transition tables, PMUTTs)自动生成的模型,以表达相邻音高旋律元的链接概率,为 旋律计算提供基本数据.分别定义了用来自动生成新的音高旋律元、乐节、乐句、乐曲的4个旋律计算的算子,以自动生成乐曲.实验结果表明, 与以音符为基本单位的马尔可夫作曲方法相比,以音高旋律元为基本单位进行作曲可以提高旋律的逻辑严密性和美感度.     

一种新型的音乐信息检索索引方法及其应用

本文提出一种新型的音乐信息检索索引方法,并将其应用于哼唱检索系统上,获得可喜的成果。该方法根据音乐旋律的特点,使用音高和音长描述一段乐曲。考虑到各种音乐输入方式存在的音高不一致性和节奏伸缩性,系统根据乐曲旋律特征的总体变化,将平均音高差和平均音长变化百分比作为关键字建立M树索引结构。由于各类输入旋律常常存在误差,本文定义一定的搜索半径,查找半径范围内与输入的音乐片断最相似的音乐文件。实验结果表明,该结构可以使系统提高60%以上的检索速度,并且搜索结果的正确率最高仍然可达80%。     

基于定性映射的哼唱音乐旋律提取

根据哼唱旋律提取的特点和定性映射的相关知识,结合基本乐理,提出哼唱片段旋律提取的定性映射模型和算法,包括哼唱旋律音符切分阈值的动态定性判定,以及音符音高确定的动态赋权的定性映射。实验结果表明,该算法不仅能灵活合理地确定音符切分的定性判定基准,同时能够较准确地提取音符音高,并得到哼唱片段的旋律轮廓线。     

基于复Morlet小波的地层钻探识别

在低信噪比时,短时傅里叶变换和实小波变换无法准确提取钻头进入不同地层的时延信息。为此,提出一种复小波变换分析法。利用幅值和相位信息对信号突变点进行提取和定位,从而实时判断钻头钻进目的层的时刻。实验结果表明,该方法能准确表征振动信号的时频特征,与短时傅里叶变换和实小波变换相比,具有更好的时间定位和抑噪能力。     

基于哼唱的音乐检索应用系统

通过研究哼唱旋律基频提取和检索算法,给出了一个完整的基于哼唱的音乐检索系统框架。系统主要分析了旋律特征提取和近似旋律匹配部分。旋律特征提取部分采用基于差分Mel倒谱法求基频;旋律匹配部分对经典的动态时间弯折算法原理分析后,根据声音特征引入音长差序列的余弦相似度,提高了检索效率和精度。在340首MIDI歌曲的测试集上,前三位识别效率提高3.7%,用时降低16%,系统的性能有明显改善。     

A repeating pattern based Query-by-Humming fuzzy system for polyphonic melody retrieval

Query-by-Humming involves retrieving music with a melody that matches the hummed query. An improved Query-by-Humming system for extracting pitch contour information based on a fuzzy inference model is introduced. In addition, an improved content-based music repeating pattern extraction model is introduced. Our bar-indexing method can extract the melody, identify repeating patterns and handle polyphonic MIDI files. To verify the effectiveness of the system, 15 volunteers recorded queries that were fed as input to the system and the longest common subsequence (LCS) was used to identify the most related top N matches. The system achieves 70% accuracy among the top 5 items retrieved.     

有效的哼唱旋律基音提取方法研究与实现

为使用户可以通过哼唱音乐片段的方式,在较大规模乐曲库中能实时、准确、快速搜索到目标歌曲,结合多种音乐的乐理特点和音乐的数字化表示,提出考虑周期性测度改进传统端点检测方案,并综合线性预测分析（LPC）和相关函数与削波法相结合的方法进行旋律基音提取。实验表明利用LPC仅仅保留声门激励信号的特点,有效地减少了声道共振峰的影响,而采用削波法也一定程度减少噪声的干扰并使得计算相关函数的运算量大为减少,更显著的是考虑周期性测度的端点检测可以找到更精确的语音段,可以准确提取旋律并有效达到哼唱检索实时性要求。     

基于稀疏表示分类器的和弦识别研究

和弦识别作为音乐信息标注的基础,在分析音乐结构和旋律方面具有非常重要的作用.结合音乐理论知识,提出一种基于稀疏表示分类器的和弦识别方法.与传统的基于帧的识别方法不同,以节拍作为和弦变化的最小时间间隔,利用CQT (Constant-Q Transform)变换对音乐信号进行时频分析,提取PCP (Pitch Class Profile)特征,采用稀疏表示分类器(Sparse Representation-based Classification,SRC)进行和弦识别.实验结果表明,提出的特征和识别方法在识别率上均高于传统的方法.     

利用互信息实现音乐风格的分类

提出了一种基于相对音高和相对时延表达音乐旋律的模型,这种模型能够更好地反映不同演奏方式下的同一旋律型。基于上述表达模型提出的音乐风格分类算法通过旋律互信息度量音乐风格,同Unigram和Bigram模型的切分算法具有相近的时间复杂度,能够更好地支持具有多种音乐风格的乐曲分类。     

基于分层次聚类的MIDI音乐主旋律提取方法

为了准确提取多音轨MIDI主旋律,同时减小主旋律分布在乐器音轨或音高较弱部分所产生的提取误差,提出了基于分层次聚类的多音轨MIDI主旋律提取方法。首先解析MIDI音乐文件,然后去除每一音轨中的控制音符和不包含旋律信息的音轨,通过归并到文该文件中的具有音高柱状图特征的音符集,从而提取出主旋律。通过与人工标识结果的实验进行比较,表明该提取主旋律方法的准确性。     

Melody extraction from music using modified group delay functions

Modified group delay based algorithms for estimation of melodic pitch sequences from heterphonic/polyphonic music are discussed in this paper. Two different variants of the modified group delay function are proposed, namely, (a) system based—MODGD (Direct) and (b) source based—MODGD (Source). In (a) the standard modified group delay function (MODGDF) is used to estimate prominent melodic pitch (\(f_0\)), which appears like a low frequency formant in the MODGDF spectrum. In (b), the power spectrum of the signal is first flattened to emphasise the source. The flattened power spectrum behaves like a sinusoid in noise, the frequency of the sinusoid being related to the pitch frequency. The modified group delay function of this signal produces peaks at \(T_0\), \(2T_0, \ldots ,\) where \(T_0=\frac{1}{f_0}\). Continuity constraints in a dynamic programming framework are imposed across frames to reduce octave errors. Sudden changes in pitch are accommodated by changing the frame size dynamically using a multi-resolution framework. The performance of the proposed systems was evaluated on four datasets: ADC-2004, LabROSA, MIREX-2008 and Carnatic music dataset. The performance of the proposed approaches demonstrate the potential of the group delay based methods for melody extraction.     

An effective music information retrieval method using three-dimensional continuous DP

This paper describes a music information retrieval system that uses humming as the key for retrieval. Humming is an easy way for a user to input a melody. However, there are several problems with humming that degrade the retrieval of information. One problem is the human factor. Sometimes, people do not sing accurately, especially if they are inexperienced or unaccompanied. Another problem arises from signal processing. Therefore, a music information retrieval method should be sufficiently robust to surmount various humming errors and signal processing problems. A retrieval system has to extract the pitch from the user's humming. However, pitch extraction is not perfect. It often captures half or double pitches, which are harmonic frequencies of the true pitch, even if the extraction algorithms take the continuity of the pitch into account. Considering these problems, we propose a system that takes multiple pitch candidates into account. In addition to the frequencies of the pitch candidates, the confidence measures obtained from their powers are taken into consideration as well. We also propose the use of an algorithm with three dimensions that is an extension of the conventional Dynamic Programming (DP)algorithm, so that multiple pitch candidates can be treated. Moreover, in the proposed algorithm, DP paths are changed dynamically to take deltaPitches and IOIratios (inter-onset-interval) of input and reference notes into account in order to treat notes being split or unified. We carried out an evaluation experiment to compare the proposed system with a conventional system . When using three-pitch candidates with conference measure and IOI features, the top-ten retrieval accuracy was 94.1%. Thus, the proposed method gave a better retrieval performance than the conventional system.