Results 11 -
16 of
16
A Novel Approach Based on Fault Tolerance and Recursive Segmentation to Query by Humming
"... With the explosive growth of digital music, content-based music information retrieval especially query by humming/singing have been attracting more and more attention and are becoming popular research topics over the past decade. Although query by humming/singing can provide natural and intuitive wa ..."
Abstract
- Add to MetaCart
With the explosive growth of digital music, content-based music information retrieval especially query by humming/singing have been attracting more and more attention and are becoming popular research topics over the past decade. Although query by humming/singing can provide natural and intuitive way to search music, retrieval system still confronts many issues such as key modulation, tempo change, note insertion, deletion or substitution which are caused by users and query transcription respectively. In this paper, we propose a novel approach based on fault tolerance and recursive segmentation to solve above problems. Music melodies in database are represented with specified manner and indexed using inverted index method. Query melody is segmented into phrases recursively with musical dictionary firstly. Then improved edit distance, pitch deviation and overall bias are employed to measure the similarity between phrases and indexed entries. Experimental results reveal that proposed approach can achieve high recall for music retrieval.
A Survey on Query by Singing/Humming
"... Performing comparison search in huge databases is a difficulty of particular concern in several communities, such as music, database, and data mining. A number of query by humming/singing (QBH) systems have evolved in recent years, which can search for the song without manual input. Query by humming ..."
Abstract
- Add to MetaCart
(Show Context)
Performing comparison search in huge databases is a difficulty of particular concern in several communities, such as music, database, and data mining. A number of query by humming/singing (QBH) systems have evolved in recent years, which can search for the song without manual input. Query by humming systems will return a structured list of songs according to the similarity between humming and intent song according to the given melodies hummed by the users. Query by humming uses a content-based music information retrieval (MIR) method which is an efficient way to search the song from a large database. This paper is focused on providing a brief overview of query by singing/humming systems and methods are available in literature.
Article Multi-Classifier Based on a Query-by-Singing/Humming System
"... symmetry ..."
(Show Context)
RESEARCH Open Access Intelligent query by humming system based on score level fusion of multiple classifiers
"... Recently, the necessity for content-based music retrieval that can return results even if a user does not know information such as the title or singer has increased. Query-by-humming (QBH) systems have been introduced to address this need, as they allow the user to simply hum snatches of the tune to ..."
Abstract
- Add to MetaCart
(Show Context)
Recently, the necessity for content-based music retrieval that can return results even if a user does not know information such as the title or singer has increased. Query-by-humming (QBH) systems have been introduced to address this need, as they allow the user to simply hum snatches of the tune to find the right song. Even though there have been many studies on QBH, few have combined multiple classifiers based on various fusion methods. Here we propose a new QBH system based on the score level fusion of multiple classifiers. This research is novel in the following three respects: three local classifiers [quantized binary (QB) code-based linear scaling (LS), pitch-based dynamic time warping (DTW), and LS] are employed; local maximum and minimum point-based LS and pitch distribution feature-based LS are used as global classifiers; and the combination of local and global classifiers based on the score level fusion by the PRODUCT rule is used to achieve enhanced matching accuracy. Experimental results with the 2006 MIREX QBSH and 2009 MIR-QBSH corpus databases show that the performance of the proposed method is better than that of single classifier and other fusion methods.
Model
"... Extracting the main melody from a polyphonic music recording seems natural even to untrained human listeners. To a certain extent it is related to the concept of source separation, with the human ability of focusing on a specific source in order to extract relevant information. In this article, we p ..."
Abstract
- Add to MetaCart
Extracting the main melody from a polyphonic music recording seems natural even to untrained human listeners. To a certain extent it is related to the concept of source separation, with the human ability of focusing on a specific source in order to extract relevant information. In this article, we propose a new approach for the estimation and extraction of the main melody (and in particular the leading vocal part) from polyphonic audio signals. To that aim, we propose a new signal model where the leading vocal part is explicitly represented by a specific source/filter model. The proposed representation is investigated in the framework of two statistical models: a Gaussian Scaled Mixture Model (GSMM) and an extended Instantaneous Mixture Model (IMM). For both models, the estimation of the different parameters is done within a maximum likelihood framework adapted from single-channel source separation techniques. The desired sequence of fundamental frequencies is then inferred from the estimated parameters. The results obtained in a recent evaluation campaign (MIREX08) show that the proposed approaches are very promising and reach state-of-the-art performances on all test sets.
ABSTRACT Title of dissertation: SPARSE AND NONNEGATIVE FACTORIZATIONS FOR MUSIC UNDERSTANDING
"... In this dissertation, we propose methods for sparse and nonnegative factorization that are specifically suited for analyzing musical signals. First, we discuss two constraints that aid factorization of musical signals: harmonic and co-occurrence constraints. We propose a novel dictionary learning me ..."
Abstract
- Add to MetaCart
(Show Context)
In this dissertation, we propose methods for sparse and nonnegative factorization that are specifically suited for analyzing musical signals. First, we discuss two constraints that aid factorization of musical signals: harmonic and co-occurrence constraints. We propose a novel dictionary learning method that imposes harmonic constraints upon the atoms of the learned dictionary while allowing the dictionary size to grow appropriately during the learning procedure. When there is significant spectral-temporal overlap among the musical sources, our method outperforms popular existing matrix factorization methods as measured by the recall and precision of learned dictionary atoms. We also propose co-occurrence constraints – three simple and convenient multiplicative update rules for nonnegative matrix factorization (NMF) that enforce dependence among atoms. Using examples in music transcription, we demonstrate the ability of these updates to represent each musical note with multiple atoms and cluster the atoms for source separation purposes. Second, we study how spectral and temporal information extracted by nonnegative factorizations can improve upon musical instrument recognition. Musicalinstrument recognition in melodic signals is difficult, especially for classification systems
