Music information retrieval in compressed audio files: a survey

Perceived predominant melody of music is the most convenient and memorable description and can be used for content-based music retrieval. However, including human voice and multiple musical instruments playing together, it is difficult to extract a predominant contour of pitches directly from MP3 music recordings. In order to build a similarity music melody model, several audio files, whose melody is perceptually similar, are collected in our experiment. Many features are extracted and a melodic similarity model is defined through analyzing each feature and combinations of them. The melody model is evaluated based on classification results of six categories of Chinese folk music using Support Vector Machine. The experiment results show that 36-dimensional Constant Q Transform (CQT) feature can represent the melody of audio music pieces accurately. Further more, the classification results for audio data with similar melody are good enough to be used in audio music classification or segmentation and subsequently are very helpful in music information retrieval system.

Music Recognition System has becoming popular these days. They are based on either audio or symbolic method, which compares the user's query with the existing music database. The investigation has shown that the audio-based method system is good for storing sound waves. However, the limitation is to illustrate the content of the music. The symbolic-based method system doing well in representing the content of the music, including recognize similar patterns, but limitation in creating the music, e.g., Electronic Music. We also carried some detailed tests based on the previous Neural Network systems, with Music Definition Language (MDL) and Music Manipulation Language (MML). Furthermore, we have tested our previous classification system with new melody query, to see how it can handle with external music pieces, which beyond the self-testing from a self-organising-map. The conclusion is that our system can classify variation type, including key variations, expansion and reduction, which is better than those existing Music Information Retrieval (MIR) systems.

Current Music Information Retrieval (MIR) systems focus on melody based retrieval with some tolerance for user errors in the melody specification. The system described here presents a novel method for theme retrieval: A theme is described as a list of musical events, containing melody and harmony features, which must be presented in a given order and within a given time frame. The system retrieves musical phrases that fit the description. A system of this type could serve musicians and listeners who wish to discover thematically similar phrases in music digital libraries. The prototype and underlying model have been tested on midi sequences of music by W.A. Mozart and have shown good performance results.

This paper introduces the Raga Based Music Classification as a part of Music Information Retrieval (MIR) systems for retrieving musical information. The music has been more than just a sound that entertains us. MIR users like musicology researchers, musicians, music learners, music therapists, etc., require not just the sound but the actual strength of the music that controls our body, motivates us, cures mental illness, etc. The backbone of any form of music is its raga. A raga is a particular combination of notes with certain laws which, when carefully observed, preserves and safeguards their integrity and create wonders in music. The existing MIR systems and audio search engines concentrate on content based audio mining and not ragas. This paper discusses the classification of ragas and how it differs in Carnatic, Hindustani and Western musical forms. It also describes the various features that can be extracted from an audio data to represent a raga. Finally, we propose a system architecture to perform raga based classification of music.

This study was conducted at the Music Library of the Ministry of Information (ML-MOI) and the Music Library of the Cultural Affairs (ML-CA) of Eritrea. The main aim of the study was to designan appropriate Indigenous Music Information Storage and Retrieval System for Eritrea. A quantitative approach was mainly used to obtain data from a purposefully selected sample. The qualitative approach was also used in some research stages. Methods used included documentanalysis, questionnaire, personal interview, focus group discussion and observation. It was found that music data was recorded in a register, which also served as a finding aid. Users’ preference was to search for music by artist, title, producer, occasion, subject or language.Unfortunately this was not possible with the system that was being used since it only allowed searching through the name or initials of an artist. The paper recommends the establishment of an automated indigenous storage and retrieval system to enable registration of indigenous knowledge information, offering facilities for indexing, searching and report generation.

Recently, several music information retrieval (MIR) systems which retrieve musical pieces by the user's singing voice have been developed. All of these systems use only melody information for retrieval, although lyrics information is also useful for retrieval. In this paper, we propose a new MIR system that uses both lyrics and melody information. First, we propose a new lyrics recognition method. A finite state automaton (FSA) is used as recognition grammar, and about 86% retrieval accuracy was obtained. We also develop an algorithm for verifying a hypothesis output by a lyrics recognizer. Melody information is extracted from an input song using several pieces of information of the hypothesis, and a total score is calculated from the recognition score and the verification score. From the experimental results, 95.0% retrieval accuracy was obtained with a query consisting of five words.

\nAs computer technology develops rapidly, retrieval systems have also undergone great changes. People are no longer contented with singular retrieval means, but are trying many other ways to retrieve feature content. When it comes to music, however, the complexity of sound is still preventing its retrieval from moving further forward. To solve this problem, systematic analysis and study is carried out on music retrieval system based on feature content. A music retrieval system model based on feature content consisting of technical approaches for processing and retrieving of extraction symbols of music feature content is built and realized. An SML model is proposed and tested on two different types of song sets. The result shows good performance of the system. Besides, the shortfalls of the model are also noted and the future prospects of the music retrieval system based on feature content are outlined.\n

In this paper, a music instrumentation analysis and identification method is proposed. In contrast to existing systems, it tries to identify the whole instrument set in polyphonic music and also decide whether each instrument actually dominates at a particular moment or not, but without calculating the exact pitch, onset timing, or the volume of each note. Moreover, it does not require the music source separation in advance. We address this problem by incorporating the beatsynchronous scheme with fuzzy clustering to analyze the instrument components. Experiments show that the instrument identification process results in an 85.19% averaging recognition rate, which is comparable with other existing systems. In addition, it generates the extra time-varying instrumentation information. This information can be considered as a new mid-level feature in music information retrieval systems.

Bag of Features (BoF) has been successfully exploited in content-based image retrieval for several years. Due to its performance and popularity, several extensions have been proposed that involve feature description, dictionary building, feature encoding and post-query process, etc. This paper proposes a dynamically weighting scheme for BoF-based image retrieval based on feedback. It involves two contributions: (i) analyzing the statistical distribution characteristic of similar BoF representations and (ii) computing weights dynamically based on the feedback obtained from different initial query results. We quantitatively evaluate the proposed method on two different databases. Experiments confirm that the proposed weighting scheme has better performance than the baseline of BoF-based image retrieval systems. Meanwhile, the results demonstrate the effectiveness of the weighting scheme in terms of the precision of top-N returned images.

Music similarity can be perceived by the listeners in different ways depending on individual preferences to musical parameters. Metadata based similarity measures are used by many websites for music recommendation and retrieval. Metadata attached to music files as text generally include title, albums, genre, artist etc. The main limitation of this method is that it can only work if metadata is available with the music. It may produce wrong results if incorrect metadata is associated with the music file. Present Meta data based systems also lack in analyzing contents. We have conducted experiments with Indian film songs in pairs and triplets to understand listener's perception of similarity. We analyzed content based parameters such as voice, mood, instruments used, lyrics, rhythms, tune etc and their relative importance in similarity perception to majority of the listeners. We propose to use both metadata and content based parameters. We worked on few parameters and worked with some algorithms in our prototype. Our findings can be useful for music Information Retrieval System and the concept is applicable to all musical forms. Perception based framework for music similarity is an attempt to model present and future needs of music listeners with option of adjustment for various musical parameters from listener perceptive.

Lots of work has been done on speech and speaker recognition. Many technologies were developed for the analysis of speech waveforms. Musical instrument recognition is an important aspect of music information retrieval system. In this paper we analyzed features for musical instruments recognition and a brief study on music similarity. Music similarity search is done by using mel-frequency cepstral coefficients (MFCC), linear predictive coefficients (LPC) and the classifier used is K- Nearest Neighbor with Dynamic Time Warping.

Music information retrieval (MIR) systems tend to fall into two camps: that camp developing cataloging and providing advanced access systems for large collections of music and that camp developing specific query or access mechanisms. We have started to merge these camps by integrating Variations2, which provides access to a digitized portion of Indiana University's vast music library, with Michigan's VocalSearch, which provides a query-by-humming (QBH) search engine. The joint system, V2V, demonstrates how QBH can be used in connection with a large number of holdings in a real-world environment.

Raga is a soul of Indian Music and the Indian Music has been studied on the basis of Raga. It can also be the main parameter for content based retrieval of audio in Music Information Retrieval(MIR) system. In Western music, melody has not many variations, but in Indian music melody has many variations in the form of ragas. Difficulty in understanding the complex structure of raga makes automatic Raga Identification problem a critical one. Many different attempts have been made to address the raga identification problem but realization of such a system for a large collection of raga is a long way to go. There are many issues in regard to this that need to be solved. We have designed solution to tackle two issues in our work and present the methods and the experimental analysis in this paper. The first issue is to handle the large number of raga classes which is solved through the clustering technique based on jump sequence. The second issue that is addressed here is avoiding the calculation of the scale (tonic) of the song to identify the notes in the song. So approaching a method where raga identification can be done even without knowing tonic (scale) of the song. We present the importance of jump sequence in raga identification in this paper. We also present the experimental results on naturally clustering the ragas along with cluster identification for a given song.

The main objective of the project is to build a system that allows users to predict genre as well as language out of some music . The Automated determination of musical genre and linguistic categorization is a machine learning based prediction model which is used to predict the genres and languages of an audio . Musical genres are categorical labels created by humans to characterize piece of music. A musical genre is characterized by common characteristics typically related to the instrumentation, rhythmic structure and harmonic content of the music. The performance and relative importance of the proposed features are investigated by training the statistical pattern recognition classifiers using real world audio collections and using machine learning algorithm.In this project, we built systems called music genre and language classification and the effects of different feature extraction methods and their various combinations were also investigated. This task is of great interest in music information retrieval and recommendation systems. In recent years, several machine learning algorithms have been developed to tackle this task, using features such spectral, temporal, and tonal characteristics of audio signals. Music genre prediction and language classification is a task that involves automatically predicting a piece of music into a specific genre category as well as language based on its audio features. Keywords-machine-learning,music,music genre and language classification

Quantification of stylistic differences between musical artists is of academic interest to the music community, and is also useful for other applications such as music information retrieval and recommendation systems. Information about stylistic differences can be obtained by comparing the performances of different artists across common musical pieces. In this article, we develop a statistical methodology for identifying and quantifying systematic stylistic differences among artists that are consistent across audio recordings of a common set of pieces, in terms of several musical features. Our focus is on a comparison of ten different orchestras, based on data from audio recordings of the nine Beethoven symphonies. As generative or fully parametric models of raw audio data can be highly complex, and more complex than necessary for our goal of identifying differences between orchestras, we propose to reduce the data from a set of audio recordings down to pairwise distances between orchestras, based on different musical characteristics of the recordings, such as tempo, dynamics, and timbre. For each of these characteristics, we obtain multiple pairwise distance matrices, one for each movement of each symphony. We develop a hierarchical multidimensional scaling (HMDS) model to identify and quantify systematic differences between orchestras in terms of these three musical characteristics, and interpret the results in the context of known qualitative information about the orchestras. This methodology is able to recover several expected systematic similarities between orchestras, as well as to identify some more novel results. For example, we find that modern recordings exhibit a high degree of similarity to each other, as compared to older recordings.