No full-text available
To read the full-text of this research,
you can request a copy directly from the authors.
Time-Slot Based Intelligent Music Recommender in Indian Music
Abstract
Music listening is one of the most common thing of human behaviors. Normally mobile music is downloaded to mobile phones and played by mobile phones. Today millennial people use mobile music in about all the age groups. Music recommendation system enhances personalized music classifications that create a profile with the service and build up a music library based on the choice preferences using mobile cloud services. Music recommendation through cloud is therefore an emerging field, and this can be done using various parameters like song genre similarity, human behavior, human mood, song rhythmic patterns, seasons etc. In this article an intelligent music recommender system that identifies the raga name of one particular song music and then mapping with the raga time database and classify the songs according to their playing time and create time slot based personalized music libraries.
... in a day [6,24]. Hence, the previous discussions are a little bit tricky and limited to the Indian classical music context. ...
... Authors have deployed an intelligent music recommender system that recognizes the raga name and map raga time database of the raga patterns. The classification technique has been projected based on the playing time for personalized and create a time slot based personalized music libraries [6]. Researchers have proposed a Deep Temporal Neural Music Recommendation system inspired musical features and the temporal preferences of the users. ...
Music has emerged to be of paramount importance to humanity and is not only considered as a source of entertainment but also an agent that causes social and psychological influences. A large number of existing digital music libraries have improved awareness among people through the music recommendation approach. However, several critical technical challenges still require attention and must be well–addressed to provide a reliable recommendation to music listeners. In Indian Classical Music, Raga is composed of coalescing diverse musical note structures. The history of classical music unveils that every raga possesses some distinct sessions. With a vast collection of classical music files in online music libraries, locating and listening to classical music is no more a difficult task. However, searching and listening to the audio of one’s preference may not be simple as it must instinctively satisfy the listener’s preference in a precise session. In this paper, a system termed as iMusic has been proposed to classify, analyze, and recommend the session–sensitive performance of Indian classical music by analyzing the musical note structures followed by features matching. Available note-patterns in the raga performance have been illustrated using a deep neural network and a set of machine learning algorithms where raga samples have been represented as inputs in the projected network and are classified based on the performing sessions. A context-aware k-means clustering algorithm has also been illustrated, entitled as a data filtering algorithm. The proficiency of the filtering algorithm has been established in two ways. Primarily, as a data-sensitive analysis, and second as empirical studies on synthetically obtained real classical music dataset (https://github.com/SamarjitRoy89/iMusic.git) to put on the hybrid music recommendation. In this work, a case-study of session-sensitive Indian music recommender system has been demonstrated using key-strategies viz. listener modelling, representation learning, and music profiling. Eventually, several evaluation metrics have been discussed to characterize the effectiveness of proposed representation learning-based playing session-sensitive music recommendation strategies. The proposed iMusic system renders data classification accuracy of ~ 88%. Such a framework could provide a useful basis regarding studies on hybrid music recommendation systems based on the usefulness of end-users.
Music has two fundamental elements like the rhythm and melody. Rhythm is a perfect arrangement of notes that is the most inseparable component of music containing the length of note structures in a musical composition. Knowledge sharing on rhythmic patterns and their applications for creating new Music is a difficult task for learners of musicology. The memetic algorithm has been shown to be very effective in finding near-optimum solutions to the modeling of rhythmic patterns. The tournament selection strategy of evolutionary algorithms has been used to construct the fruitful rhythmic patterns for music composition. The work has been introduced to identify the parent rhythms and then create the versatile offspring rhythms using memetic algorithm. The tournament selection mechanism has been initiated for parent rhythms selection process for generating offspring rhythmic structures.
The paper introduces an intelligent method to find the density and complexity of music rhythm in the context of Indian Music. Musical rhythm is a piece of unit that consists of a set of the musical beats and it has a great capacity to refresh our minds. Rhythm density and rhythm complexity are the two most important factors that determine the rhythm quality metric. Hence, computation of those two factors from a given rhythm structure is a very crucial task. This paper presents an application using some mathematical measures to generate rhythm density and complexity metrics. The main aim of this work is that it has the great impact in the field of computational musicology in Indian music.
Used the probe tone method to quantify the perceived hierarchy of tones of North Indian music. Indian music is tonal and has many features in common with Western music. However, the primary means of expressing tonality in Indian music is through melody, whereas in Western music it is through harmony (the use of chords). Probe tone ratings were given by Indian and Western listeners in the context of 10 North Indian ra_=gs (a standard set of melodic forms). These ratings confirmed the predicted hierarchical ordering. Both groups of listeners gave the highest ratings to the tonic and the 5th degree of the scale. The ratings of both groups of listeners generally reflected the pattern of tone durations in the musical contexts. This result suggests that the distribution of tones in music is a psychologically effective means of conveying the tonal hierarchy to listeners whether they are familiar with the musical tradition. Only the Indian listeners were sensitive to the scales (tha_=ts) underlying the ra_=gs. There was little evidence that Western listeners assimilated the pitch materials to the major and minor diatonic system of Western music. (34 ref)
Along with the rapid expansion of digital music formats, managing and searching for songs has become significant. Though music information retrieval (MIR) techniques have been made successfully in last ten years, the development of music recommender systems is still at a very early stage. Therefore, this paper surveys a general framework and state-of-art approaches in recommending music. Two popular algorithms: collaborative filtering (CF) and content-based model (CBM), have been found to perform well. Due to the relatively poor experience in finding songs in long tail and the powerful emotional meanings in music, two user-centric approaches: context-based model and emotion-based model, have been paid increasing attention. In this paper, three key components in music recommender - user modelling, item profiling, and match algorithms are discussed. Six recommendation models and four potential issues towards user experience, are explained. However, subjective music recommendation system has not been fully investigated. To this end, we propose a motivation-based model using the empirical studies of human behaviour, sports education, music psychology.
Early 1980's MIDI technology coming into being, it has created condition for the development of modern music technology. From the MIDI, computer music, multimedia music to music computer and network teaching, it has already played an important role in music education concept and the reform of the teaching means. In the higher music college's teaching, the best solution to realize the music teaching means modernization development is the configuration and application of multimedia teaching systems. We have the analysis and introduction on the teaching system hardware and software configuration and their in music teaching, creation, scientific research and management application.
The paper proposes a new concept to develop real time identification of an Indian Classical Raga over the Internet. To develop the aforesaid concept we are using concept of Human Computer Intelligent Interaction (HCI) and Social Cognitive Theory (SCT) to make a virtual environment from where a participant can easily recognize a note or a Raga only by a little effort. To make the server computer aware of different musical notes and Ragas we have to provide a Supervised Training and for the note recognition technique, we are using the Hidden Markov Models (HMMs). To get the expected output we are using the Viterbi Algorithm. To examine our methodology to develop the concept we are taking the help from some commercial software like MATLAB, AUDACITY and PRAAT.
Melodic motifs form essential building blocks in Indian Classical music. The motifs, or key phrases, provide strong cues to the identity of the underlying raga in both Hindustani and Carnatic styles of Indian music. Automat-ic identification and clustering of similar motifs is rele-vant in this context. The inherent variations in various instances of a characteristic phrase in a bandish (compo-sition) performance make it challenging to identify simi-lar phrases in a performance. A nyas svara (long note) marks the ending of these phrases. The proposed method does segmentation of phrases through identification of nyas and computes similarity with the reference charac-teristic phrase.
Improvisation in North Indian tabla drumming is similar to speech insofar as it is bound to an underlying system of rules determining correct sequences. The parallel is further reinforced by the fact that tabla music may be represented with an oral notation system used for its transmission and, occasionally, performance. Yet the rules are implicit and available only through the musicians' ability to play correct sequences and recognise incorrect ones. A linguistic model of tabla improvisation and evaluation derived from pattern languages and formal grammars has been implemented in the Bol Processor, a software system used in interactive fieldwork with expert musicians. The paper demonstrates the ability of the model to handle complex structures by taking real examples from the repertoire. It also questions the relevance of attempting to model irregularities encountered in actual performance.
Due to the rapid growth of internet broadband access and proliferation of
modern mobile devices, various types of multimedia (e.g. text, images, audios
and videos) have become ubiquitously available anytime. Mobile device users
usually store and use multimedia contents based on their personal interests and
preferences. Mobile device challenges such as storage limitation have however
introduced the problem of mobile multimedia overload to users. In order to
tackle this problem, researchers have developed various techniques that
recommend multimedia for mobile users. In this survey paper, we examine the
importance of mobile multimedia recommendation systems from the perspective of
three smart communities, namely, mobile social learning, mobile event guide and
context-aware services. A cautious analysis of existing research reveals that
the implementation of proactive, sensor-based and hybrid recommender systems
can improve mobile multimedia recommendations. Nevertheless, there are still
challenges and open issues such as the incorporation of context and social
properties, which need to be tackled in order to generate accurate and
trustworthy mobile multimedia recommendations.
This article may be used for research, teaching, and private study purposes. Any substantial or systematic reproduction, redistribution, reselling, loan, sub-licensing, systematic supply, or distribution in any form to anyone is expressly forbidden. The publisher does not give any warranty express or implied or make any representation that the contents will be complete or accurate or up to date. The accuracy of any instructions, formulae, and drug doses should be independently verified with primary sources. The publisher shall not be liable for any loss, actions, claims, proceedings, demand, or costs or
This Special Issue is dedicated to explicate and discuss methodological issues in the interdisciplinary research field of mathematical and computational approaches to music. It arose from a lively panel discussion at the third International Conference on Mathematics and Computation in Music 2011 in Paris. We have organized this panel in order to initiate the much needed interdisciplinary dialogue on the How, Why, and What of our modelling of and theorizing about music in the wide field of science, humanities and cognitive approaches to music research. From the contributions of the three panelists to this Special Issue, we extract key topics that the interdisciplinary scientific community needs to address in order to enable the different disciplines to productively complement one another in achieving a comprehensive approach to music as a complex, yet fundamental human trait.
We describe a realtime system that can listen to perfor- mances of tabla and identify the strokes as they are played. The system stores this information along with onset times in a symbolic score that is used as the basis for resynthe- sis and transformation. We describe playback and trans- formation possibilities of this system. Finally, we propose that such a system can be generalized with very few mod- ifications to a variety of performance scenarios involving percussion interaction.
This article is concerned with investigating some aspects of the usefulness of using genetic algorithms (GAs) for musical composition and to highlight some of their limitations. It also demonstrates the limited amount of work done so far in examining the output of GAs used in creative applications, rather than simply describing the architecture and functionality of such an algorithm, and the limited scope of work that has been undertaken. The article examines some approaches in musicology and composition that may help us to understand further how GAs could be applied to creative music tasks, and presents the IndagoSonus system as one possible application.
We have created a network that allocates a new computational unit whenever an unusual pattern is presented to the network. This network forms compact representations, yet learns easily and rapidly. The network can be used at any time in the learning process and the learning patterns do not have to be repeated. The units in this network respond to only a local region of the space of input values.
The network learns by allocating new units and adjusting the parameters of existing units. If the network performs poorly on a presented pattern, then a new unit is allocated that corrects the response to the presented pattern. If the network performs well on a presented pattern, then the network parameters are updated using standard LMS gradient descent.
We have obtained good results with our resource-allocating network (RAN). For predicting the Mackey-Glass chaotic time series, RAN learns much faster than do those using backpropagation networks and uses a comparable number of synapses.
Alternative approaches are explored and dis- cussed relating to the design and function of the software project "Nodal". This project aims to create a graphical environment that enables the user to configure a spatial, di- rected graph that generates music in real- time. We refer to such graphs as composition or nodal networks. These networks provide a programming and visualization structure that emphasizes temporal relations and event topology ñ the primary reasons for using networks to represent musical processes. The discussion in this paper relates to the initial design constraints that have been imposed on the project and alternatives within these con- straints that give rise to different musical behaviors. Assessments are made about the effectiveness of different design approaches.
In algorithmic music composition, a simple technique involves selecting notes sequentially according to a transition table that specifies the probability of the next note as a function of the previous context. An extension of this transition-table approach is described, using a recurrent autopredictive connectionist network called CONCERT. CONCERT is trained on a set of pieces with the aim of extracting stylistic regularities. CONCERT can then be used to compose new pieces. A central ingredient of CONCERT is the incorporation of psychologically grounded representations of pitch, duration and harmonic structure. CONCERT was tested on sets of examples artificially generated according to simple rules and was shown to learn the underlying structure, even where other approaches failed. In larger experiments, CONCERT was trained on sets of J. S. Bach pieces and traditional European folk melodies and was then allowed to compose novel melodies. Although the compositions are occasionally pleasant, and are preferred over compositions generated by a third-order transition table, the compositions suffer from a lack of global coherence. To overcome this limitation, several methods are explored to permit CONCERT to induce structure at both fine and coarse scales. In experiments with a training set of waltzes, these methods yielded limited success, but the overall results cast doubt on the promise of note-by-note prediction for composition.
Rag is the central melodic concept of Indian art music. The current system classifies segments from rag performances beginning at the signal level based on a spectrally derived tone profile. A tone profile is essentially a histogram of note values weighted by duration. The method is shown to be highly accurate (100% accuracy) even when rags share the same scalar material and when segments are drawn from different instruments and different points in the performance. Rag identification has important applications in automatic transcription, genre classification and musical database queries.
Today, a large number of audio features exists in audio retrieval for different purposes, such as automatic speech recognition, music information retrieval, audio segmentation, and environmental sound retrieval. The goal of this chapter is to review latest research in the context of audio feature extraction and to give an application-independent overview of the most important existing techniques. We survey state-of-the-art features from various domains and propose a novel taxonomy for the organization of audio features. Additionally, we identify the building blocks of audio features and propose a scheme that allows for the description of arbitrary features. We present an extensive literature survey and provide more than 200 references to relevant high-quality publications.
Existing music recommendation systems rely on collabora-tive filtering or content-based technologies to satisfy users' long-term music playing needs. Given the popularity of mo-bile music devices with rich sensing and wireless communi-cation capabilities, we present in this paper a novel approach to employ contextual information collected with mobile de-vices for satisfying users' short-term music playing needs. We present a probabilistic model to integrate contextual in-formation with music content analysis to offer music recom-mendation for daily activities, and we present a prototype implementation of the model. Finally, we present evalua-tion results demonstrating good accuracy and usability of the model and prototype.
Evidence has suggested that music can improve behavioural performance in several domains, including intelligence. Scientists have also discovered that music can modify the brain at both functional and structural levels. Such neural changes can impact several domains, but one domain seems to be particularly influenced by music—namely, language. Music and language seem to share special features that allow music to improve and shape language processing. This review will first discuss neuroimaging findings related to music training or musical expertise. Then, the influence of music on language processing outcomes will be considered. Finally, we will look into several future directions at the theoretical level, focusing on the relationship between music and language. Also, it will be argued that there are plausible applications for such findings, in particular when considering music as a rehabilitation tool. Music and Language: A Review of Recent Neuroscience Research and Applied Future Directions The possibility of an influence of music on cognition is a relatively new notion in psychology and neuroscience. Researchers have explored this link and discovered that musical expertise (e.g., studies with musicians versus non-musicians) or musical training (e.g., studies with non-musicians who learn music) can improve behavioural performance and modify brain substrates, not only in the musical domain but also in other domains. This new understanding of the relationship between music and cognition is helping scientists understand the effects of environmental influences on human cognition more broadly. By studying the effect of music on human cognition, scientists have begun to learn about the power of music. The general public has also become interested: 'Music makes you smarter' or 'Music helps you to learn other languages'—these are examples of common thoughts pertaining to questions about the influence of music.
In this work we propose a method to identify the raga of a Carnatic music signal. Raga is analogous to melody in Western music but is much richer and stronger in its representation. The main motive behind Raga identification is that it can be used as a good basis for music information retrieval of Carnatic music songs or Film songs based on Carnatic music. The input polyphonic music signal is analyzed and made to pass through a signal separation algorithm to separate the instrument and the vocal signal. After extracting the vocal signal we segment the vocal signal using our proposed segmentation algorithm. Using our proposed singer identification algorithm we determine the singer to know the fundamental frequency of the singer. The frequency components of the signal are then determined and we map these frequency components into the swara sequence and thereby determine the Raga of the particular song, which could be used to index the songs and further for retrieval based on the Raga.
A system was constructed to automatically identify raags using pitch-class (PCDs) and pitch-class dyad distributions (PCDDs) derived from pitch-tracked performances. Classification per-formance was 94% in a 10-fold cross-validation test with 17 target raags. Using PCDs alone, performance was 75%, and 82% using only PCDDs. Best performance was attained us-ing a maximum a posteriori (MAP) rule with a multivariate normal (MVN) likelihood model. Each raag was divided into non-overlapping 30 second segments and pitch tracked us-ing the Harmonic Product Spectrum (HPS) algorithm. Pitch tracks were then transformed into pitch-class sequences by segmenting into notes using a complex-domain detection func-tion. For each note, pitch-class was determined by taking the mode of the detected pitches from the onset of the note to the next onset. For the given tuning, the nearest pitch was found based on a just-intoned chromatic scale. The comparison was made in the log-frequency domain. PCDs and PCDDs were estimated from each segment leading to 12 PCD features and 144 PCDD features. Thus, each segment was represented by a 156-dimensional feature vector, representing the relative frequency of pitch-classes and pitch dyads. It was found that performance improved significantly (+15%) when principal component analysis was used to reduce the feature vector di-mension to 50. The study suggests that PCDs and PCDDs may be effective features for raag classification. However, the database size must be expanded in size and diversity to con-firm this more generally.
When using a mobile music player en-route, usually only little attention can be paid to its handling. Nonetheless it is desirable that all music stored in the device can be accessed quickly, and that tracks played in a sequence should match up. In this paper, we present an approach to satisfy these con-straints: a playlist containing all tracks stored in the music player is generated such that in average, consecutive pieces are maximally similar. This is achieved by applying a Traveling Salesman algo-rithm to the pieces, using timbral similarities as the distances. The generated playlist is linear and circular, thus the whole collection can easily be browsed with only one input wheel. When a cho-sen track finishes playing, the player advances to the consecutive tracks in the playlist, generally playing tracks similar to the chosen track. This behavior could be a favorable alternative to the well-known shuffle function that most current devices – such as the iPod shuffle, for example – have. We evaluate the fitness of four different Traveling Salesman algorithms for this purpose. Evaluated aspects were runtime, the length of the resulting route, and the genre distribution entropy. We implemented a Java applet to demonstrate the application and its usability.
This paper addresses the adoption of Petri Nets (PNs) in order to describe music processes. On the one hand, such formalism can be used to represent the results coming from the analysis of already existing music works. On the other hand, Petri Nets provide a formal tool to generate new music pieces. This paper is the evolution of an earlier work presented at CMMR 2005, where analytical and descriptive possibilities of Petri Nets were explored in music field. The focus of this paper is writing music by Petri Nets, and the last section will show a case study of PN-based composition.
We describe a realtime tabla generation system based on a variable-length n-gram model trained on a large symbolic tabla database. A novel, parametric smoothing algorithm based on a family of exponential curves is introduced to control the relative weight of high-and low-order models. This technique is shown to lead to improvements over a back-off smoothing for our tabla database. We find that cross-entropy is lowest when the coefficient of the exponen-tial curve is between 1 and 2 and increases for values outside of this optimal range. The basic n-gram model is extended to model dependencies between duration, stroke-type, and meter using cross-products in a Multiple Viewpoints (MV) framework, leading to improvements in most cases when compared with independent stroke and duration models.
Petri Nets are modeling tools that are used in an enormous number of real-world simulations and scientific problems. The primary objective of this paper is establishing that Petri Net is one important tool that represents quality music compositional analysis process. In this work this has been illustrated how music structures can be processed by means of a more abstract kind of representation and allow to explicitly describing the process of computational modeling of Musicology that present the attempt on music composition from the fundamental musical objects like vocal and rhythmic cycles usage using Petri Net. This attempt has been obtained to answer the query that whether Petri Net is an adequate tool for modeling such a complex process as a complete composition of music from the fundamental musical objects like vocal and rhythmic structures is. The main focus behind this work is to explore that Petri nets can be used as a good basis for retrieval of music information in World Music.
Petri Nets are the modeling tools which are exploited in a large number of real-world simulations and scientific researches. The prime intention of this contribution is being ascertained that the Petri Net is the significant tool that corresponds to the high performance quality music compositional analysis with its expressive graphical and analytical approaches as Petri nets have wide acceptance in the computational model field. In this effort, this has been represented how music structures can be progressed through a more conceptual demonstration and consent to unambiguously describe the process of computational modeling of Musicology which present the attempt on music composition from the elementary musical objects like vocal and rhythmic cycles usage using Petri Nets. This manner proposes 90% accuracy level using performance evaluation technique of the derived outcomes in Computational music modeling.
Petri nets are suitable for modelling of discrete-event systems with highly parallel and cooperating activities. In complex man-made systems, such as manufacturing systems, the systems' specific properties, such as conflicts, deadlocks, limited buffer sizes, and finite resource constraints can be easily represented in the Petri net model. Therefore teaching of Petri net basics is an inevitable component of courses on modelling and simulation. The paper presents an object oriented Matlab m-script based Petri net tool, which is used to implement Petri net examples within MMT-server e-learning environment. The tool structure is described, and basic examples on timed Petri net simulation and simulation-based optimization of schedules are provided.
We use time series analysis methods to detect differences between individuals and expertise groups in continuous perceptions of the arousal expressed by Wishart's electroacoustic piece Red Bird. The study is part of a project in which we characterise dynamic perception of the structure and affective expression of music. We find that individual series of perceptions of expressed arousal often show considerable periods of stasis. This may challenge conventional time series methodologies, so we test their validity by application of a general linear autoregressive moving average (GLARMA) approach, which supports it. Acoustic intensity is a dominant predictor of perceived arousal in this piece. We show that responses are time-variant and that animate sounds influence the conditional variance of perceived arousal. Using vector autoregression and cross-sectional time series analysis (which preserves the integrity of each individual response series), we find differences between musical expertise groups (non-musicians, musicians, and electroacoustic musicians). Individual differences within each group are greater than those between expertise groups. The companion paper applies the developed methods to all four pieces in our overall project (Dean, R.T., F. Bailes, and W.T.M. Dunsmuir. 2014. “Shared and Distinct Mechanisms of Individual and Expertise-Group Perception of Expressed Arousal in Four Works.” Journal of Mathematics and Music 8 (3): 207–223). An Online Supplement is available at http://dx.doi.org/10.1080/17459737.2014.928752.
The present article addresses the subject of music in the pedagogy of mathematics from the perspective of two researchers in mathematical music theory (MMT) belonging to mathematics departments. Our first main topic is the popularization project concerning music and mathematics of the Royal Spanish Mathematical Society, and its extension to an international level is proposed. Secondly, we present some ideas and outlines for the creation of didactic material for mathematics courses within the framework of MMT.
Musical pattern recognition and classification of the features of Indian Classical Music plays a decisive ingredient in the musicological and ethno-musicological research and development. In the conformist Indian Classical Music (ICM) has two basic bare bones, namely, the raga which is the musical scale (classical mode) and the unambiguous rhythm which proceeds as an adornment on the music. We are going to thrash out of the representation and analysis of rhythmic features of Indian Classical Music in object-oriented manner. Inheritance is one of the cornerstones of Object-Oriented Programming (OOP) concept. This is a mechanism by which the objects of one class conquer the possessions and the textures of the other class or classes owing to evade the complexities of the feature classification. The numerous formations like single, multilevel and hierarchical models of inheritance are accredited to be modeled and analyzed the rhythmic patterns of Indian Classical Music.
Pattern recognition in rhythm of Tabla instrument in ICM (Indian Classical Music) is very complex task that is the combination of speech, audio, and their signal processing techniques. In this paper we proposed a system that identify the basic source rhythm and then modify the rhythm to improve the quality of source rhythm by using Genetic Algorithm. In simple terms, rhythm is a word that refers to the length of each note in a piece of music, the combination of beats. In order to develop high quality of rhythm in an efficient manner, it is essential to identify the correct sequence of the different PRAKAR of Tabla rhythm like, THEKA, UTHAN, TUKADA, RELA, LAGGI, KAIDA, TIHAI, CHAKRADAR, etc. PRAKAR means different sorts of rhythmic compositions used in Tabla. The focus of this study is to explore the efficiency of Genetic Algorithm to search for an optimum combination of rhythm to improve the Music Quality Metric.
Raag is formed from different and correct combination of notes depending on which the Indian Classical Music is defined. Thhat is the parent class of raag. All raags belong to thhat. In Indian Classical music there are ten thhats. Each raag can be created from any of the ten thhats. Each thhat consist of special note structure. In this paper by using the notes of a song, a procedure which can determine the thhat to which that song belongs is proposed.
Polymorphism is a property of the object-oriented technology and design. The polymorphism generally provides the designing of a generic interface which embraces a set of related activities. In Indian Classical Music (ICM), there are several features by which the unique features are classified into the Super-Class and a set of Sub-classes using the object-oriented programming and analysis methodology. In this paper, the simple polymorphic approach is being gone to represent using the concept of 'Taal'. Taal is a sole feature which is abbreviated in ICM to define as the exact rhythm of the music. The soul of the music, the Taal and its variations (known as 'lay') are represented into the several Super-class and Sub-classes.
Musical pattern recognition is a challenging area of research as music is a combination of audio and speech; a signal of a particular music cannot be expressed through a linear expression only. For this reason musical pattern identification by mathematical expressions is critical. In this paper a new method is being proposed for cataloguing different melodious audio stream into some specific featured classes based on object oriented modeling. The classes should have some unique features to be specified and characterized; depending upon those properties of a particular piece of music it can be classified into different classes and subclasses. The concept is developed considering the non-trivial categorization problem due to vastness of Indian Classical Music (ICM). It can be expected that the novel concept can reduce the complication to the objective analysis of the classification problem of ICM as well as the world music.
storage capacity and the cost of the storage devises gives raise to voluminous music collection management. Various MIR techniques exist, but getting the required songs from large collection of music files, is still a challenging problem. Getting the required songs from voluminous collection with good recall and precision depends on good annotation, indexing and retrieval techniques. Among this annotation plays a vital role in developing an efficient and effective retrieval system. Tag bases annotation or the low level feature based annotations retrieval systems performance is very poor, though the processing is very simple. Semantic concept based annotation, indexing and retrieval techniques are trying to fill the gap between the machine understanding and the human preferences. This raises the need for semantic based annotation of film songs. Ontology plays a major role in semantic web and information retrieval. This raises the need for an ontology based annotation generation tool for film songs. The current research designs and implements a tool M- SAGT -Music Semantic Annotation Generation Tool. Which is flexible, user friendly and ontology based semantic annotations can be generated and stored in RDF/XML format. The generated semantic annotations can be used in semantic indexing and retrieval, which will enhance the performance of the retrieval system.
The authors present a suite to assist in the creation of musical pieces, whose foundation lies on fractals, fuzzy logic and expert systems. Even though algorithmic music has been explored, some gaps still exist. The favored approach has consisted in mapping numbers to notes to create appealing pieces. This, we contend, is a necessary but not a sufficient condition. Our suite, besides the necessary mapping, possesses the following advantages. First, it is possible to define notes, tempos, and notes durations. Notes evolve according to the selected fractal. Tempos and durations can remain fixed or they also can follow a fractal. Second, it is possible to translate the resultant fractal notes into notes belonging to a musical scale. This is done by firing appropriate rules in a rule base. Third, interpretation templates are provided. Also, melodies or harmonies are available. The suite currently contains several known fractal systems, and we also proposed one dynamical, recursive computation based on Mamdani fuzzy rule bases. The suite we present helps promoting and monitoring the creative process of composing musical scores. The actual implementation of the suite was done on the Java language.
It has been attempted to develop a neurocomputing paradigm for artificial music composition in Indian style. A musical organization, comprising a melodic pattern, a rhythmic pattern and a melody violation part, has been considered for this purpose. A simple feed forward hybrid neural network with a functional link hidden layer has been so designed as to integrate such a musical organization with Indian raga rules. The proposed artificial neural network can output a variety of compositions on any raga by generating random link weights that shape the musical organization in various ways within the freedom available in the raga framework. The neural network can be customized with specifications of any raga for outputting a large variety of musical sequences that abide by the particular raga rules. In an interactive mode, a musician user may compose non-classical and light classical songs in Indian style based on desired ragas. An evaluation of such outputs from the system on Hindustani music, as done by a group of musicians, is encouraging. The present system, when run in an “Auto Mode”, may also serve as a generator of “semi-finished” music for composing music of non-traditional structure.
This article deals with a spectrographic analysis of the singer's formant as occurred during singing of the vowels /a/, /i/, and /o/ in North Indian classical vocal music. The resonance balance, center frequency, and band-width are shown as a function of fundamental frequency for eight singers.
Two new parameters have been defined viz. asymmetry parameter (A) and spectral energy balance (W). Their variation with fundamental frequency is shown.
We consider the problem of automatic tabla transcription, specifically, the reconstruction of a score-like notation that represents timbral categories and rhythmic values. To that end, a computer-based representation for tabla is proposed that allows for encoding, analysis, and typesetting. A transcription system consisting of modules for onset detection, stroke timbre recognition, and rhythm detection was created. Performance was evaluated on a large database taken from three performers under different recording conditions, containing a total of 16,834 strokes. First, the time-domain signal was segmented using complex-domain thresholding that looked for sudden changes in amplitude and phase discontinuities. 98% of onsets were detected against a 1% false positive rate. Classification of strokes was performed using a maximum a posteriori (MAP) rule with a multivariate normal likelihood distribution (MVN), and using non-parametric techniques such as probabilistic neural networks (PNN), feed-forward neural networks (FFNN), and tree-based classifiers. Two evaluation protocols were used. The first used 10-fold cross validation. The recognition rate averaged over many experiments that contained 10-15 classes was 92% for the MVN, 94% for the FFNN and PNN, and 84% for the tree-based classifier. To test generalization, a more difficult independent evaluation was undertaken in which no test strokes came from the same recording as the training strokes. The average recognition rate over a wide variety of test conditions was 76% for the MVN, 83% for the FFNN, 76% for the PNN, and 66% for the tree-based classifier. To determine rhythmic values for strokes, stroke durations were expressed in terms of the beat period (seconds/beat), which was estimated by taking the auto-correlation of the onset detection function, as well as by a duration histogram method. Quantization of durations was done by rounding to a discrete grid constructed by duple and triple divisions of the beat. Accurate rhythmic notation was demonstrated for five tabla phrases containing a total of 552 rhythmic values. Preliminary results using the three modules in series to create a full transcription system yielded good results on the five examples. Finally we describe challenges and possible solutions for the development of a robust, fully automatic transcription system.
Tonal modulation is discussed in the context of graph theory with the aim of applying its fundamental ideas and theorems to solve or pose musically interesting problems. Mathematical ideas such as connectivity of graphs, group structure, graph colouring, metrics, Hamiltonian paths and Euler tours are used to prove the existence of special sequences of modulations and chord progressions, as well as to investigate the possibilities and limitations of tonal modulation.
L-Systems have traditionally been used as a popular method for the modelling of space-filling curves, biological systems and morphogenesis. In this paper, we adapt string re-writing grammars based on L-Systems into a system for music composition. Representation of pitch, duration and timbre are encoded as grammar symbols, upon which a series of re-writing rules are applied. Parametric extensions to the grammar allow the specification of continuous data for the purposes of modulation and control. Such continuous data is also under control of the grammar. Using non-deterministic grammars with context sensitivity allows the simulation of Nth-order Markov models with a more economical representation than transition matrices and greater flexibility than previous composition models based on finite state automata or Petri nets. Using symbols in the grammar to represent relationships between notes, (rather than absolute notes) in combination with a hierarchical grammar representation, permits the emergence of complex music compositions from a relatively simple grammars.