Die automatische Klassifikation von Musik in Genres wird seit einigen Jahren systematisch erforscht. In dieser Zeit wurden Genre-Klassifikationssysteme und ihre Komponenten immer weiter verbessert, wofür die verschiedensten Richtungen eingeschlagen wurden. Diese Arbeit gibt deshalb im ersten Teil einen umfassenden Überblick über das Forschungsgebiet der Genre-Klassifikation, von den grundlegenden Techniken bis zum aktuellen Forschungsstand. Im zweiten Teil der Arbeit wird ein neuartiger Ansatz vorgestellt, der das Ziel hat, die Genre-Klassifikation gegen eventuelle Störungen robuster zu machen. Dies soll durch die gezielte Erkennung und Ausfilterung von Bereichen, in denen das Musikstück einer Veränderung seiner Charakteristik unterliegt, realisiert werden. Eine Implementation dieses Ansatzes wird an einer Musikkollektion mit fünf Genres evaluiert und die Ergebnisse werden ausführlich analysiert.

Since the 1970s, music librarians have been discussing the challenges of cataloging music media. In the 1990s, they began work on a Music Thesaurus to provide a multi-faceted approach to indexing, cataloging, and retrieving music media. In 1999 Indiana University proposed a digital music library, to allow for better indexing and retrieval in addition to content-based music retrieval. In 2000, a commercial venture, The Music Genome Project ©, began cataloging sound recordings of popular music by hundreds of musical characteristics and has created a user interface that allows listeners to enter the title and artist of a certain piece of music and receive recommendations for similar music to then purchase via Pandora.com. The following paper will address the question: how might current analyzing and classifying methods be used to provide additional indexing that facilitates retrieval and use of sound recordings by special populations, specifically professionals treating children with Asperger’s syndrome?

Die automatische Klassifikation von Musik in Genres wird seit einigen Jahren systematisch erforscht. In dieser Zeit wurden Genre-Klassifikationssysteme und ihre Komponenten immer weiter verbessert, wofür die verschiedensten Richtungen eingeschlagen wurden. Diese Arbeit gibt deshalb im ersten Teil einen umfassenden Überblick über das Forschungsgebiet der Genre-Klassifikation, von den grundlegenden Techniken bis zum aktuellen Forschungsstand. Im zweiten Teil der Arbeit wird ein neuartiger Ansatz vorgestellt, der das Ziel hat, die Genre-Klassifikation gegen eventuelle Störungen robuster zu machen. Dies soll durch die gezielte Erkennung und Ausfilterung von Bereichen, in denen das Musikstück einer Veränderung seiner Charakteristik unterliegt, realisiert werden. Eine Implementation dieses Ansatzes wird an einer Musikkollektion mit fünf Genres evaluiert und die Ergebnisse werden ausführlich analysiert.

傳統的音樂檢索系統主要在提供使用者特定音樂的查詢(target search)。除此之外，使用者也有類型音樂查詢(category search)的需求。在類型音樂查詢中，該類型的所有音都共同具備使用者所定義的概念(semantic concept)。這個由使用者定義的概念在音樂檢索系統上是主觀的且動態產生的。換句話說，同一使用者在不同情境之下對於同一首音樂可能產生不同的解讀概念。為了動態擷取使用者的概念，讓使用者參與在查詢過程的互動機制是必要的。因此， 我們提出將相關回饋(relevance feedback)的機制運用在以內容為主的音樂查詢系統上，讓系統從使用者的相關回饋中學習使用者的概念，並利用這學習出的概念來幫助音樂查詢。 由於使用者可能從整首音樂或音樂片段兩種角度來判斷該音樂是否具備使用者定義的概念。因此，本論文提出用以片段為主的音樂模型(segment-based modeling approach)將音樂表示成音樂片段的集合。進一步再從整首音樂和片段中擷取特徵。 其次，我們針對該問題提出相關演算法來探勘使用者的概念。該演算法先從相關和不相關的音樂資料庫中個別探勘常見樣式，再利用這些樣式建立分類器以區分音樂的相關性。 最後，我們分析各種系統回饋機制對搜尋效果的影響。Most-positive回傳機制會選擇根據目前系統判斷為最相關的物件。Most-informative機制則是回傳系統無法判斷其相關性的音樂物件。Most-informative 機制的目的在增加每回合系統從使用者身上得到的資訊量。Hybrid 則是中和前兩種機制的優點。本文中，我們模擬並比較各種回傳機制的效能。實驗結果顯示相關回饋機制確實能提升查詢的效果。 / Traditional content-based music retrieval system retrieves a specific music object which is similar to the user’s query. There is also a need, category search, for retrieving a specific category of music objects. In category search, music objects of the same category share a common semantic concept which is defined by the user. The concept for category search in music retrieval is subjective and dynamic. Different users at different time may have different interpretations for the same music object. In the music retrieval system along with relevance feedback mechanism, users are expected to be involved in the concept learning process. Relevance feedback enables the system to learn user’s concept dynamically. In this paper, the relevance feedback mechanism for category search of music retrieval based on the semantic concept learning is investigated. We proposed a segment-based music representation to assist the system in discovering user’s concept in terms of low-level music features. Each music object is modeled as a set of significant motivic patterns (SMP) achieved by discovering motivic repeating pattern. Both global and local music features are considered in concept learning. Moreover, to discover user’s semantic concept, a two-phase frequent pattern mining algorithm is proposed to discover common properties from relevant and irrelevant objects respectively and based on which a classifier is derived for distinguishing music objects. Except user’s feedback, three strategies of the system’s feedback to select objects for user’s relevance judgment are investigated. Most-positive strategy returns the most relevant music object to the user while most-informative strategy returns the most uncertain music objects for improving the discrimination power of the next round. Hybrid feedback strategy returns both of them. Comparative experiments are conducted to evaluate effectiveness of the proposed relevance feedback mechanism. Experimental results show that a better precision can be achieved via proposed relevance feedback mechanism.

抽取出音樂當中的近似重複樣式來做音樂檢索可以減少要比對的資料量，但是使用者若使用沒有重複的旋律來查詢便會有找不到歌曲的情況。另一方面，將音樂分段成phrase可以減少樹狀索引結構的空間，亦可減少查詢處理時間，但是使用者的查詢若是跨越phrase的，也將影響查詢結果。 在本論文中，我們比較了以近似重複樣式與phrase兩種不同的音樂特徵用來做音樂檢索的效果以及效率。根據實驗顯示，使用者的查詢是重複旋律的機會大於單一phrase，所以用近似重複樣式作為音樂查詢比對資料效果是比phrase好的。而在1-D List索引結構下，近似重複樣式的效率也優於phrase。除此之外，本論文也提出了一個新的近似重複樣式抽取方法，實驗證明我們的方法是有效的。 / Extract the approximate repeating pattern from music data will decrease the volumes of music data that need to be tested when music retrieve. If the user’s query is not a repeating melody, it can’t retrieve the music that the user wants correctly. In addition, segment the music by phrase will decrease the space that tree-like index structure need, and also decrease the retrieval processing time. If the user’s query is not a single phrase, it will influence the effectiveness of retrieval. In this thesis, we compare the effectiveness and efficiency of music retrieval methods with two different music features (approximate repeating pattern and phrase). According to experiment results, the probability that user’s query is repeating melody is more than the probability that user’s query is a single phrase. Therefore, we are of the opinion that the effectiveness that use approximate repeating pattern to process retrieval is more prominent than the effectiveness that phrase to process retrieval. Furthermore, the efficiency that use approximate repeating pattern to process retrieval is more outstanding than use phrase under 1-D List index structure. Besides, a new approximate repeating pattern extraction method is proposed. Experiment results show that our approximate repeating pattern extraction method can work correctly.

隨著數位多媒體技術的進步，越來越多的音樂以數位化的方式來儲存，數位音樂的檢索成為重要的研究領域之一。以內容為主的音樂檢索(Content-Based Music Retrieval, CBMR)能讓使用者直接利用音樂的內容做檢索，而非傳統以音樂的metadata查詢的方法。目前有關CBMR的研究，常見的查詢方式包括哼歌、唱歌或打拍子等。但是，這些方法都會因為查詢者缺乏音樂訓練而無法正確表達出想查詢的音樂，影響查詢效果。 人們常常會根據曲風將音樂分類，音樂曲風的探勘將有助於CBMR的研究。本篇論文主要目的在結合多媒體與資料探勘的技術，從大量MIDI音樂中，作音樂曲風的探勘及分類，並將曲風探勘的技術應用在個人化音樂推薦、音樂風格檢索及音樂風格瀏覽上。 在本論文的第一部份，音樂曲風探勘分類的研究，包括了三個研究議題：音樂特徵的粹取、頻繁樣式的探勘及曲風的分類。我們利用和絃作為音樂的特徵，根據和聲學的原理，從MIDI音樂中找出主旋律搭配的和絃。粹取出和絃後，我們研究不同的和絃特徵表示法與其頻繁樣式探勘演算法。針對所探勘出的頻繁樣式，我們修改associated classification演算法，以應用在音樂曲風的分類上。此外，不同的曲風，其風格的多樣性也不同。因此，為了提高分類的效果，我們提出Single-Type Variant-Support (STVS) 與Multi-Type Variant-Support (MTVS) classification演算法，使得分類規則中允許多種特徵表示與不同的最小支持度。 在本篇論文的第二部分，我們應用曲風探勘的技術，提出了個人化音樂推薦的機制。針對使用者對音樂風格的喜好，將新的音樂推薦給使用者。系統根據使用者對資料庫中音樂的存取行為，學習使用者在音樂曲風上的偏好，產生個人化的2-way preference classifier，以推薦符合使用者喜好的音樂。 第三部分為音樂曲風的檢索。目前大部分的CBMR系統中，使用者僅能尋找已經聽過的音樂。然而，使用者想查詢的很可能是沒聽過，但曲風感覺類似的音樂。針對上述的問題，我們提出了以音樂曲風作檢索的新方法。同時，我們提出四種曲風查詢的描述方式，並且利用音樂風格探勘與分類的技術產生的分類規則計算曲風的相似度，最後依照曲風的相似程度產生檢索結果。 本篇論文的最後一部分為音樂風格的分群。音樂風格的分群有助於瀏覽大量的音樂資料。我們利用和絃為特徵，針對不同的特徵表示方法，提出相似度的計算方式。我們將數種分群演算法應用於音樂風格的分群上，並比較各種分類演算法與不同的音樂特徵與表示法的分群效果。 / With the development of multimedia technology, digital music is now in widespread use. Content-based music retrieval (CBMR) has attracted much interest in recent years. CBMR allows users query by music content rather than metadata. However, even with the capability of query by humming, the effectiveness of CBMR system suffers from the ability of query content expression for people without music training. Music style is one of the features that people used to classify music. Discovery of music style is helpful for the design of content-based music retrieval systems. In this thesis, we investigate the mining techniques of music style by melody from a collection of MIDI music and apply the mining techniques to three applications, personalized music filtering, music retrieval by melody style and music style browsing. In the first part, the design issues of melody style mining and classification consist of the feature extraction, frequent pattern mining and melody style classification. We extracted the chord from the melody based on the harmony and investigated the representation of extracted features. For each extracted feature, the corresponding frequent pattern mining techniques are developed. For the melody style classification algorithm, we propose the Single-Type Uniform-Support classification (STUS) algorithm which is modified from the associated classification algorithm. To improve the performance of classification, we propose two new classification algorithms - Single-Type Variant-Support Classification (STVS) and Multi-Type Variant- Support classification (MTVS) algorithm. STVS learns the appropriate minimum supports of every category’s frequent patterns automatically. MTVS algorithm considers all types of frequent patterns for every category further and can decide the appropriate combination of frequent patterns and the corresponding minimum supports. In the second part, we present a personalized content-based music filtering system to support music recommendation based on user’s preference of melody style. The system learns the user preference by mining the melody patterns from the music access behavior of the user. A two-way melody preference classifier is therefore constructed for each user. Music recommendation is made through this melody preference classifier. Performance evaluation showed that the filtering effect of the proposed approach meets user’s preference. A new approach for CBMR by the semantic property of music – melody style is proposed in the third part of this thesis. Most CBMR systems provide users the capability to look for music that has been heard. However, sometimes, listeners are looking, not for something they already know, but for something new. Moreover, people sometimes wish to retrieve music that “feels like” another music object or a music style. We propose four types of query specification for melody style query. The output of the melody style query is a music list ranked by the degree of relevance to the query. We adopted melody style mining and classification rule learning algorithm to obtain style classification rules. The style ranking is determined by the style classification rules. In this thesis, we also investigate music clustering techniques which are useful to browse large music archives. We propose the similarity measures for the representation of the extracted chord-sets and compared the performance of different clustering algorithms with various extracted features.

No description available.

在本論文中我們提出了一種個人化情緒／情境音樂檢索方法。主要的概念為根據使用者的feedback來找出符合該使用者情緒／情境的音樂在features上所具備的特性，藉此達到個人化的效果。為了更明確表示出音樂的特性，我們利用統計features分布情況的方式來做為音樂的表示法。同時，定義了兩層features自動weighting的方法來決定每個feature在不同情緒／情境下的鑑別度。最後，我們將探討音樂特性與音色對不同的情緒／情境會造成什麼樣的影響，並試著分析音樂與情緒／情境間的關係。 / In this paper, an approach for personalized music retrieval based on emotions / situations is proposed. The main concept is to find out the properties of music that caused the user have emotions / situations responses via the user feedback. And using the user feedback will help us to establish a personalized music retrieval system based on emotions / situations. To represent the music properties clearly, we proposed a new method of music representation based on statistics. And we defined a two-phase features re-weighting method to find out the importance of features in different emotions / situations. At last, we will discuss the influence of music properties and timbre on different emotions / situations, and try to analyze the relationship between the emotions / situations.