• Corpus ID: 32536578

Spot the odd song out : similarity model adaptation and analysis using relative human ratings

  title={Spot the odd song out : similarity model adaptation and analysis using relative human ratings},
  author={Daniel Wolff},
Understanding how listeners relate and compare pieces of music is a fundamental challenge in music research as well as for commercial applications: Today’s large-scale applications for music recommendation and exploration utilise various models for similarity prediction to satisfy users’ expectations. Perceived similarity is specific to the individual and influenced by a number of factors such as cultural background and age. Thus, adapting a generic model to human similarity data is useful for… 
Predicting the emotions expressed in music
A two-alternative forced-choice experimental paradigm to quantify expressed emotions in music using the two wellknown arousal and valence (AV) dimensions is introduced and the importance of modeling subjects individually due to significant subjective differences is shown.
Representation decomposition for knowledge extraction and sharing using restricted Boltzmann machines
This thesis introduces confidence rules, which are used to allow the combination of symbolic knowledge and quantitative reasoning in RBMs, and introduces a novel algorithm for transfer learning called “Adaptive Profile Transferred Likelihood”, which adapts transferred representations to target domain data.
Freesound Datasets: A Platform for the Creation of Open Audio Datasets
Comunicacio presentada al 18th International Society for Music Information Retrieval Conference celebrada a Suzhou, Xina, del 23 al 27 d'cotubre de 2017.


Harvesting microblogs for contextual music similarity estimation: a co-occurrence-based framework
It is shown that collaborative chatter on music can be effectively used to develop music artist similarity measures, which are a core part of every music retrieval and recommendation system.
Similarity Based on Rating Data
An algorithm to measure the similarity of two multimedia objects, such as songs or movies, using users’ preferences, and shows how this approach works by measuring its performance using an objective metric based on whether the same artist performed both songs.
From Low-Level to High-Level: Comparative Study of Music Similarity Measures
This work proposes two distance measures based on tempo-related aspects and a high-level semantic measure based on regression by support vector machines of different groups of musical dimensions such as genre and culture, moods and instruments, or rhythm and tempo.
Music Recommendation and Discovery in the Long Tail
The Long Tail curve of artist popularity is model to predict —potentially— interesting and unknown music, hidden in the tail of the popularity curve, which has significant implications for recommender systems that assist users to explore the Long Tail, digging for content they might like.
The perception and cognition of musically similar songs is a well-known research topic in the music information retrieval (MIR) community. There has been much work in the auditive area. More recent
Supporting Folk-Song Research by Automatic Metric Learning and Ranking
It is shown how a weighted linear combination of different basic similarity measures can be automatically adapted to a specific retrieval task by learning this metric based on a special type of constraints.
Learning the Similarity of Audio Music in Bag-of-frames Representation from Tagged Music Data
This paper introduces a Gaussian mixture model (GMM) as the encoding reference for BOF modeling, and proposes a novel learning algorithm to minimize the similarity gap between low-level acoustic features and music tags with respect to the prior weights of the pre-trained GMM.
MUSIPER: a system for modeling music similarity perception based on objective feature subset selection
MUSIPER is presented, a content-based music retrieval system which constructs music similarity perception models of its users by associating different music similarity measures to different users through a user-supplied relevance feedback procedure and related neural network-based incremental learning.
Methodological Considerations in Studies of Musical Similarity
A novel system through which users can specify by example the context and focus of their retrieval needs is introduced, and the design of a study is details to find parameters for the system which can also be adapted to test the system as a whole.
Sequential Complexity as a Descriptor for Musical Similarity
Analysis of selected descriptors reveals that representing features at multiple time scales benefits prediction accuracy, and incorporates them into similarity rating prediction and song year prediction tasks.