Tararira: Query By Singing System

2003

Music information retrieval is a field of rapidly growing commercial interest. This paper describes TANSEN, a query-by-humming based music retrieval system under development at IIT, Bombay. Named after the legendary musician (and a tenuous acronym for "TA-Note Song Extractor-Navigator), the system is designed to accept acoustic queries in the form of sung fragments, to search a database of Indian film songs. Algorithms for the extraction of melody from the query signal, and pattern matching for search and retrieval from the database are presented. The user interface is described, and experimental results obtained on a prototype version are reported.

National Conference on Communications, Bombay, …, 2002

This paper describes some early attempts at developing a music indexing and retrieval system based on melody, or tune, of songs. In the envisaged system, the "query", a song fragment whistled or sung by the user into a microphone, is used to search a database of soundtracks to find the entry that is best matched to it in tune. The challenging issues that this project raises are described. Signal processing tools suitable for melody detection are presented, and finally some experimentally obtained results are discussed.

Lecture Notes in Computer Science, 2006

This paper investigates the problem of retrieving Karaoke music by singing. The Karaoke music encompasses two audio channels in each track: one is a mix of vocal and background accompaniment, and the other is composed of accompaniment only. The accompaniments in the two channels often resemble each other, but are not identical. This characteristic is exploited to infer the vocal's background music from the accompaniment-only channel, so that the main melody underlying the vocal signals can be extracted more effectively. To enable an efficient and accurate search for a large music database, we propose a phrase onset detection method based on Bayesian Information Criterion (BIC) for predicting the most likely beginning of a sung query, and adopt a multiple-level multiple-pass Dynamic Time Warping (DTW) for melody similarity comparison. The experiments conducted on a Karaoke database consisting of 1,071 popular songs show the promising results of query-by-singing retrieval for Karaoke music.

1997

This paper describes a system designed to retrieve melodies from a database on the basis of a few notes sung into a microphone. The system first accepts acoustic input from the user, transcribes it into common music notation, then searches a database of 9400 folk tunes for those containing the sung pattern, or patterns similar to the sung pattern; retrieval is ranked according to the closeness of the match. The paper presents an analysis of the performance of the system using different search criteria involving melodic contour, musical intervals and rhythm; tests were carried out using both exact and approximate string matching. Approximate matching used a dynamic programming algorithm designed for comparing musical sequences. Current work focuses on developing a faster algorithm.

Proc. IV IASTED International Conf. on Signal Processing, Pattern Recognition and Applications (SPPRA 2007)

Pitch extraction from singing voice has been viewed from the absolute pitch of the voice. However, for the query by humming applications, the absolute pitch is not of as much importance as that of relative pitch. This paper addresses the issue of relative pitch tracking for singing voice and attempts to improve the transcription accuracy. It also tries to bring robustness to transcription, in the several forms of querying by a user. The algorithm makes use of specially designed Bach filters which automatically associate a relative frequency with a corresponding musical semitone. This makes conversion of the transcribed pitch values to the MIDI format relatively easy. Preliminary results show up to 85% accuracy in the automated transcription when compared to manually transcription.

Technology, 2007

Query-by-Humming systems offer content-based searching for melodies and require no special musical training or knowledge. Many such systems have been built, but there has not been much useful evaluation and comparison in the literature due to the lack of shared databases and queries. The MUSART project testbed allows various search algorithms to be compared using a shared framework that automatically runs experiments and summarizes results. Using this testbed, we compared algorithms based on string alignment, melodic contour matching, a hidden Markov model, n-grams, and CubyHum. Retrieval performance is very sensitive to distance functions and the representation of pitch and rhythm, which raises questions about some previously published conclusions. Some algorithms are particularly sensitive to the quality of queries. Our queries, which are taken from human subjects in a fairly realistic setting, are quite difficult, especially for n-gram models. Finally, simulations on query-byhumming performance as a function of database size indicate that retrieval performance falls only slowly as the database size increases.

2012

This dissertation is concerned with the problem of describing the singing voice within the audio signal of a song. This work is motivated by the fact that the lead vocal is the element that attracts the attention of most listeners. For this reason it is common for music listeners to organize and browse music collections using information related to the singing voice such as the singer name. Our research concentrates on the three major problems of music information retrieval: the localization of the source to be described (i.e. the recognition of the elements corresponding to the singing voice in the signal of a mixture of instruments), the search of pertinent features to describe the singing voice, and finally the development of pattern recognition methods based on these features to identify the singer. For this purpose we propose a set of novel features computed on the temporal variations of the fundamental frequency of the sung melody. These features, which aim to describe the vib...

Intl Joint Conferences on …, 2007

Abstract. Retrieval performance in query-by-humming (QBH) systems depends crucially on the accurate note segmentation and labeling of user queries. To facilitate note segmentation, querying is often restricted to the easily detected syllable “ta”, which is not necessarily the syllable ...

2002

In this paper, a new system for the automatic transcription of singing sequences into a sequence of pitch and duration pairs is presented. Although such a system may have a wider range of applications, it was mainly developed to become the acoustic module of a queryby-humming (QBH) system for retrieving pieces of music from a digitized musical library. The first part of the paper is devoted to the systematic evaluation of a variety of state-of-the art transcription systems. The main result of this evaluation is that there is clearly a need for more accurate systems. Especially the segmentation was experienced as being too error prone ( ¾¼ % segmentation errors). In the second part of the paper, a new auditory model based transcription system is proposed and evaluated. The results of that evaluation are very promising. Segmentation errors vary between 0 and 7 %, dependent on the amount of lyrics that is used by the singer. The paper ends with the description of an experimental study that was issued to demonstrate that the accuracy of the newly proposed transcription system is not very sensitive to the choice of the free parameters, at least as long as they remain in the vicinity of the values one could forecast on the basis of their meaning.

The International journal of Multimedia & Its Applications, 2012

Query by Singing/Humming (QBSH) is a Music Information Retrieval (MIR) system with small audio excerpt as query. The rising availability of digital music stipulates effective music retrieval methods. Further, MIR systems support content based searching for music and requires no musical acquaintance. Current work on QBSH focuses mainly on melody features such as pitch, rhythm, note etc., size of databases, response time, score matching and search algorithms. Even though a variety of QBSH techniques are proposed, there is a dearth of work to analyze QBSH through query excerption. Here, we present an analysis that works on QBSH through query excerpt. To substantiate a series of experiments are conducted with the help of Mel-Frequency Cepstral Coefficients (MFCC), Linear Predictive Coefficients (LPC) and Linear Predictive Cepstral Coefficients (LPCC) to portray the robustness of the knowledge representation. Proposed experiments attempt to reveal that retrieval performance as well as precision diminishes in the snail phase with the growing database size.