Query by humming: musical information retrieval in an audio database

By A. Ghias, Jonathan Logan, David Chamberlin, B. Smith. 1995

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Pretrained Transformers for Text Ranking: BERT and Beyond (2020, background): “ly important. We only consider queries that are expressed in text, although in principle queries can be presented in different modalities, for example, speech31 or images, or even “query by humming” [Ghias et al., 1995]. Nevertheless, to enable automated processing, information needs must be encoded”
A survey of temporal data mining (2006, background): “For example, given a large music database the user could " hum " a query and the system should retrieve tracks that resemble it (Ghias et al 1995).”
Encoding Musical Style with Transformer Autoencoders (2019, background): “We incorporate and extend upon the rich line of work for measuring music similiarity in symbolic music (Ghias et al., 1995; Berenzweig et al., 2004; Slaney et al., 2008; Hung et al., 2019; Yang & Lerch, 2018) for our setting, in which we evaluate similarities between polyphonic piano performances as”
Multimodal Video Indexing: A Review of the State-of-the-art (2004, background): “Most solutions to video indexing address the how question with a unimodal approach, using the visual [16, 28, 63, 81, 84, 98, 102], auditory [22, 26, 47, 60, 61, 65, 92], or textual modality [12, 33, 103].”
Warping indexes with envelope transforms for query by humming (2003, background): “RELATED WORK Most of the research in pre-existing query by humming systems uses pitch contour to match similar melodies [8, 5, 20, 29].”