Music Information Processing Using Continuous Speech Recognition Methods

使用连续语音识别方法的音乐信息处理

• 批准号: 14380156
• 负责人: SAGAYAMA Shigeki
• 金额: $ 10.82万
• 依托单位: The University of Tokyo
• 依托单位国家: 日本
• 项目类别: Grant-in-Aid for Scientific Research (B)
• 财政年份: 2002
• 资助国家: 日本
• 起止时间: 2002 至 2004
• 项目状态: 已结题
• 来源: https://kaken.nii.ac.jp/en/grant/KAKENHI-PROJECT-14380156/
• 关键词: continuous speech recognition; music information processing; rhythm recognition; automatic harmonization; automatic counterpoint; harmonic clustering; specmurt; 確率モデル; 時空間クラスタリング; Specmurt法; 自動和声づけ; 自動採譜; MIDI信号; 連続音声認識手法; リズムベクトル; 隠れマルコフモデ

We formulated music rhythm recognition for ranscribing MIDI data into music score as a Viterbi path search problem in HMM where hidden states and output probabilities represent the intended note values and actually played note lengths, respectively. We also solved rhythm recognition of polyphonic music by reducing polyphony intomonophony. Tempo modeling and tempo change detection were enabled with segmental k-means algorithm for speech recognition.Harmonization (chord finding) of given melodies was formulated as an isomorphic problem as continuous speech recognition by defining output by the given melody, hidden states by the chord behind the melody and stochastic language model by chord sequences. Automatic counterpoint was developed with a two-step maximum likelihood approach consisting of rhythm design and pitch allocation solved by dynamic programming.In polyphonic signal analysis, an algorithm named Harmonic-structured Clustering was developed based on the k-means clustering algorithm under harmonic constraint by modeling the framewise observed spectrum as overlapped harmonic structures and considering that the distributed energy in harmonic structure belongs to a single cluster. Furthermore, by introducing the probabilistic assignment to clusters, k-means was generalized into the EM-algorithm and attained higher performance of multi-pitch estimation. Utilizing an information criterion such as AIC, the number of sources and octave location were also enabled."Specmurt analysis" was proposed for polyphonic signal analysis. The inverse Fourier transform of linear spectrum with log-frequency was called "specmurt". Along log-scaled frequency, observed linear spectrum is regarded as convolution of distribution density of fundamental frequencies and harmonic structures of multiple tones which are assumed identical. This idea opened up a new signal processing capabilities.

我们制定了音乐节奏识别rancribing数据到乐谱作为一个维特比路径搜索问题，在HMM中的隐藏状态和输出概率分别表示预期的音符值和实际播放的音符长度。我们还解决了复调音乐的节奏识别，减少复调intonophone。采用分段k-means算法实现了克里思的速度建模和速度变化检测，通过定义给定旋律的输出、旋律后面的和弦的隐藏状态和和弦序列的随机语言模型，将给定旋律的和声（和弦发现）问题表示为连续语音识别的同构问题。自动对位法是一种两步最大似然法，它包括节奏设计和音高分配，用动态规划法求解。提出了一种基于k-提出了一种谐波约束下的均值聚类算法，该算法将帧间观测谱建模为重叠的谐波结构，并考虑谐波结构中的分布能量属于单簇。通过引入聚类的概率分配，将k-means算法推广到EM算法中，获得了更高的多基音周期估计性能。利用AIC等信息准则，还启用了源的数量和倍频程位置。提出了“谱分析法”用于复音信号的分析。对数频率的线性谱的逆傅里叶变换称为“谱”。沿沿着对数标度频率，观测线性谱被视为基频分布密度与假定相同的多个音调的谐波结构的卷积。这一想法开辟了新的信号处理能力。

项目成果

Time-Space Clustering for Multi-pitch Spectral Segregation Using Kernel Audio Stream Model

使用内核音频流模型进行多音高频谱分离的时空聚类

• 发表时间: 2005
• 期刊: The 2005 Spring Meeting of the Acoustic Society of Japan 3-7-19
• 作者: Hirokazu Kameoka;Takuya Nishimoto;Shigeki Sagayama
• 通讯作者: Shigeki Sagayama

Extraction of Multiple Fundamental Frequencies from Polyphonic Music Using Harmonic Clustering

使用谐波聚类从复调音乐中提取多个基本频率

• 发表时间: 2004
• 期刊: Proc. International Congress on Acoustics (ICA) (Kyoto, Japan)
• 作者: Hirokazu Kameoka;Takuya Nishimoto;Shigeki Sagayama
• 通讯作者: Shigeki Sagayama

調波スペクトル分離の原理Harmonic Clusteringと赤池情報量規準による多声部楽曲音響信号の同時発音数および多重ピッチの推定

使用谐波聚类、谐波频谱分离原理和 Akaike 信息准则估计复调音乐音频信号的同时语音数量和多个音高

• 发表时间: 2004
• 期刊: 日本音響学会7月音楽音響研究会資料
• 作者: 亀岡弘和;西本卓也;嵯峨山茂樹
• 通讯作者: 嵯峨山茂樹

ハーモニック・クラスタリングによる多重音信号音高抽出における音源数とオクターブ位置推定

使用谐波聚类估计多音信号基音提取中的声源数量和八度位置

• 发表时间: 2003
• 期刊: 日本音響学会2003年秋季研究発表会講演論文集
• 作者: 亀岡 弘和;西本 卓也;嵯峨山 茂樹
• 通讯作者: 嵯峨山 茂樹

確率モデルによる多声楽曲MIDI演奏からの楽譜推定

使用概率模型根据和弦 MIDI 演奏估计乐谱

• 发表时间: 2003
• 期刊: 情報処理学会研究報告 2003-MUS-50
• 作者: 武田 晴登;西本 卓也;篠田 浩一;嵯峨山 茂樹
• 通讯作者: 嵯峨山 茂樹