Semantic Annotation and Retrieval of Music and Sound Effects

By Douglas R. Turnbull, Luke Barrington, David A. Torres, Gert R. G. Lanckriet. IEEE Transactions on Audio, Speech, and Language Processing, 2008

566 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Signal Processing

View Paper: https://www.semanticscholar.org/paper/0cf464e413e1e051b535d4d42de4ecd49853053e

How researchers see this paper

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

In Artificial Intelligence

In Signal Processing

Citations in the corpus

Large Margin Metric Learning for Multi-Label Prediction (2015, background): “• cal500 (Turnbull et al. 2008): Contains songs by different artists.”
A Tutorial on Multilabel Learning (2015, methodology): “—COMPUTER AUDITION LAB 500 (CAL500) [Turnbull et al. 2008] is a dataset composed of 502 popular Western songs, represented by 68 acoustic features, each of which has been manually annotated by at least three human annotators who employed a vocabulary of 174 tags.”
On the Role of Correlation and Abstraction in Cross-Modal Multimedia Retrieval (2014, background): “Index Terms—Multimedia, content-based retrieval, multimodal, cross-modal, image and text, retrieval model, semantic spaces, kernel correlation, logistic regression Ç”
Learning Spatial Regularization with Image-Level Supervisions for Multi-label Image Classification (2017, background): “Multi-label classification has applications in many areas, such as document topic categorization [29, 10], music annotation and retrieval [35], scene recognition [4], and gene functional analysis [2].”
Efficient Multi-label Classification with Many Labels (2013, background): “• cal500 (Turnbull et al., 2008): It contains songs by different artists.”
A Survey of Audio-Based Music Classification and Annotation (2011, methodology): “[54], [55] used a hierarchical Gaussian mixture model to describe the audio features extracted from music segments”
Exploring automatic music annotation with "acoustically-objective" tags (2010, methodology): “More specifically, they were incorporated into each of the top performing autotagging systems in the 2008 MIREX tag classification task [1, 3, 13, 21].”
A Bag-of-Features Framework to Classify Time Series (2013, background): “Studies on BoF representations for time series data are limited, with few studies in audio and speech recognition literature [34], [35], [37], [38], [39].”
Addressing imbalance in multilabel classification: Measures and random resampling algorithms (2015, unknown): “0871 [26]”
State of the Art Report: Music Emotion Recognition: A State of the Art Review (2010, background): “To remedy this problem, Turnbull et al. collected the CAL500 data set of annotated music [22].”
Two-Stage Label Embedding via Neural Factorization Machine for Multi-Label Classification (2019, background): “• Cal500 (Turnbull et al. 2008): A music dataset containing human-generated musical annotations that describes 502 popular western musical tracks with 174 tags representing emotions, instruments, and other related concepts.”
FMA: A Dataset for Music Analysis (2016, methodology): “…data-heavy models such as DL. Table 1 lists the most common datasets used for dataset 1 #clips #artists year audio RWC [12] 465 - 2001 yes CAL500 [45] 500 500 2007 yes Ballroom [13] 698 - 2004 yes GTZAN [46] 1,000 ∼ 300 2002 yes MusiClef [36] 1,355 218 2012 yes Artist20 [7] 1,413 20 2007 yes…”
Multi-Label Learning with Global and Local Label Correlation (2017, background): “For example, a scene image can be annotated with several tags [1], a document may belong to multiple topics [2], and a piece of music may be associated with different genres [3].”
Machine Recognition of Music Emotion: A Review (2012, background): “The timbral of the singing voice, such as aggressive, breathy, gravelly, high-pitched,or rapping [Turnbull et al. 2008], is often directly related to our emotion perception.”