Query by humming

Published 1 January 1995

Asif Ghias, Jonathan Logan, David Chamberlin, Brian C. Smith

Citations696

TL;DR

A system for querying an audio database by humming is described along with a scheme for representing the melodic information in a song as relative pitch changes, and the performance results of system indicating its effectiveness are presented.

Abstract

The emergence of audio and video data types in databases will require new information retrieval methods adapted to the specific characteristics and needs of these data types. An effective and natural way of querying a musical audio database is by humming the tune of a song. In this paper, a system for querying an audio database by humming is described along with a scheme for representing the melodic information in a song as relative pitch changes. Relevant difficulties involved with tracking pitch are enumerated, along with the approach we followed, and the performance results of system indicating its effectiveness are presented.

Keywords

Computer Science

Discrete-Time Signal Processing

11,537 Citations1989Alan V. Oppenheim, Ronald W. Schafer

The definitive, authoritative text on DSP, written by prominent, DSP pioneers, it provides thorough treatment of the fundamental theorems and properties of discrete- time linear systems, filtering, sampling, and discrete-time Fourier Analysis.

View PDF

Springer series in information sciencesPitch Determination of Speech Signals

644 Citations1983Wolfgang Heß

Computer Music JournalListening: An Introduction to the Perception of Auditory Events

555 Citations1990Eliot Handelman, Stephen Handel

IEEE Transactions on Audio and ElectroacousticsNew methods of pitch extraction

229 Citations1968M. M. Sondhi

Three new methods will be described for the extraction of the fundamental pitch from a speech signal, which can tolerate a considerable amount of high-pass filtering and additive noise with little degradation in performance.

The Journal of the Acoustical Society of AmericaSpeech Analysis-Synthesis System Based on Homomorphic Filtering

161 Citations1969Alan V. Oppenheim

A digital speech analysis‐synthesis system based on a recently proposed approach to the deconvolution of speech is presented and either a zero‐phase or minimum‐phase characteristic can be obtained by simple weighting of the cepstrum before transformation.

IEEE Transactions on Acoustics Speech and Signal ProcessingReal-time digital hardware pitch detector

155 Citations1976J. Dubnowski, Ronald W. Schafer +1 more

Computing of the autocorrelation function of the clipped speech is easily implemented in digital hardware using simple combinatorial logic, i.e., an up-down counter can be used to compute each correlation point.

IEEE Transactions on Acoustics Speech and Signal ProcessingMaximum likelihood pitch estimation

136 Citations1976J.D. Wise, J. Caprio +1 more

Theoretical Computer ScienceEfficient string matching with k mismatches

135 Citations1986Gad M. Landau, Uzi Vishkin

An algorithm for finding all occurrences of the pattern in the text, each with at most k mismatches, runs in O( k ( m log m + n )) time.

Lecture notes in computer scienceFast and practical approximate string matching

97 Citations1992Ricardo Baeza‐Yates, Chris H. Perleberg

DSpace@MIT (Massachusetts Institute of Technology)Structure out of sound

60 Citations1993Michael Jerome Hawley

Several implementations of sound sensors are presented, including a polyphonic pitch extractor, a music detector, and a talker recognizer for indexing conversations that filter sound to produce event-list scripts that describe the contents in some sense.