Music Similarity Measures: What's the use?

By Jean-Julien Aucouturier, François Pachet. International Society for Music Information Retrieval Conference, 2002

332 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, Signal Processing

View Paper: https://www.semanticscholar.org/paper/fd0e03294616d3264564ccbbad82d37721c392c3

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

1. Lawrence Carin
2. Yoshua Bengio
3. Qiang Yang
4. Quoc V. Le
5. Trevor Darrell
6. Jianfeng Gao
7. David M. Blei
8. Yann LeCun

In Computer Vision and Pattern Recognition

1. Lawrence Carin
2. Luc Van Gool
3. Jitendra Malik
4. Yoshua Bengio
5. Dacheng Tao
6. Ming-Hsuan Yang
7. Andrew Zisserman
8. Xiaogang Wang

In Signal Processing

1. Jean-Julien Aucouturier
2. D. Ellis
3. François Pachet
4. David B. Dunson
5. Douglas Eck
6. Lawrence Carin
7. Kai Ni
8. Juan Pablo Bello

Citations in the corpus

• Recommendations : Modeling Music Ratings with Temporal Dynamics and Item Taxonomy (2011, positive): “For example, MelFrequency Cepstral Coefficients (MFCCs) are often used to generate feature vectors, which can be used to find other items with acoustic resemblance [3, 18].”
• Content-Based Music Information Retrieval: Current Directions and Future Challenges (2008, methodology): “This work was extended by Aucouturier and Pachet [ 70 ] to use Gaussian mixture models (GMM) of MFCC features.”
• Multi-Task Learning for Analyzing and Sorting Large Databases of Sequential Data (2008, methodology): “For this purpose, we use a distance measure similar to that considered by Aucouturier [24].”
• Representing Musical Genre: A State of the Art (2003, methodology): “This is surprising, especially because time-modeling (notably HMMs) has proved to be a successful framework for the related problem of “style recognition,” mentioned above (see notably recent work by Pachet, 2002).”
• A Survey of Audio-Based Music Classification and Annotation (2011, methodology): “The common choices of classifiers are K-nearest neighbor (K-NN) [116], support vector machine (SVM) [117], and GMM classifier [70].”
• Moving Beyond Feature Design: Deep Architectures and Automatic Feature Learning in Music Informatics (2012, background): “Additionally, researchers have for some time addressed the possibility that we are converging to glass ceilings in content-based areas like acoustic similarity [2].”
• Aggregate features and ADABOOST for music classification (2006, methodology): “Gaussian mixtures have also been used to generate song-level features by, e.g., Aucouturier and Pachet (2002) and Pampalk et al. (2005).”
• A Large-Scale Evaluation of Acoustic and Subjective Music-Similarity Measures (2004, methodology): “…shown to give good performance for a variety of audio classi(cid:142)cation tasks and are favored by a number of groups working on audio similarity (Blum et al. 1999; Foote 1997; Tzanetakis 2002; Logan 2000; Logan and Salomon 2001; Aucouturier and Pachet 2002; Berenzweig, Ellis, and Lawrence 2003).”
• Automatic genre classification of music content: a survey (2006, methodology): “They used a state-of-the-art timbre similarity measure [17] and a database of 20000 titles distributed over 18 genres.”
• Multi-task learning for sequential data via iHMMs and the nested Dirichlet process (2007, methodology): “For this purpose, we use a distance measure similar to that considered by Aucouturier and Pachet (2002).”