arXiv research

Improved cover song detection with neural networks.

The use of community detection algorithms is explored within the framework of cover song identification, i.e. the automatic detection of different audio renditions of the same underlying musical piece. Until now, this task has been posed as a typical query-by-example task, where one submits a query song and the system …

This paper investigates methods for quantifying similarity between audio signals, specifically for the task of of cover song detection. We consider an information-theoretic approach, where we compute pairwise measures of predictability between time series. We compare discrete-valued approaches operating on quantised au…

Automatic cover detection -- the task of finding in a audio dataset all covers of a query track -- has long been a challenging theoretical problem in MIR community. It also became a practical need for music composers societies requiring to detect automatically if an audio excerpt embeds musical content belonging to the…

We find the minimum dilatation of pseudo-Anosov braids on n-punctured discs for 3 <= n <= 8. This covers the results of Song-Ko-Los (n=4) and Ham-Song (n=5). The proof is elementary, and uses the Lefschetz formula.

Estimates the growth of Morse index for free boundary minimal hypersurfaces.

In this work, we attempt to solve the Hit Song Science problem, which aims to predict which songs will become chart-topping hits. We constructed a dataset with approximately 1.8 million hit and non-hit songs and extracted their audio features using the Spotify Web API. We test four models on our dataset. Our best model…

A model for hit song prediction can be used in the pop music industry to identify emerging trends and potential artists or songs before they are marketed to the public. While most previous work formulates hit song prediction as a regression or classification problem, we present in this paper a convolutional neural netw…

Have you ever wondered how a song might sound if performed by a different artist? In this work, we propose SCM-GAN, an end-to-end non-parallel song conversion system powered by generative adversarial and transfer learning that allows users to listen to a selected target singer singing any song. SCM-GAN first separates …

Record companies invest billions of dollars in new talent around the globe each year. Gaining insight into what actually makes a hit song would provide tremendous benefits for the music industry. In this research we tackle this question by focussing on the dance hit song classification problem. A database of dance hit …

Playlist recommendation involves producing a set of songs that a user might enjoy. We investigate this problem in three cold-start scenarios: (i) cold playlists, where we recommend songs to form new personalised playlists for an existing user; (ii) cold users, where we recommend songs to form new playlists for a new us…

We conjecture that the Joyce-Song wall-crossing formula for Donaldson-Thomas invariants arises naturally from an asymptotic expansion in the field theoretic work of Gaiotto, Moore and Neitzke. This would also give a new perspective on how the formulae of Joyce-Song and Kontsevich-Soibelman are related. We check the con…

Being able to predict whether a song can be a hit has impor- tant applications in the music industry. Although it is true that the popularity of a song can be greatly affected by exter- nal factors such as social and commercial influences, to which degree audio features computed from musical signals (whom we regard as …

State of the art music recommender systems mainly rely on either matrix factorization-based collaborative filtering approaches or deep learning architectures. Deep learning models usually use metadata for content-based filtering or predict the next user interaction by learning from temporal sequences of user actions. D…

The task of determining item similarity is a crucial one in a recommender system. This constitutes the base upon which the recommender system will work to determine which items are more likely to be enjoyed by a user, resulting in more user engagement. In this paper we tackle the problem of determining song similarity …

Paper classifies Brazilian music genres using song lyrics with BLSTM network.

This work formulates a novel song recommender system as a matrix completion problem that benefits from collaborative filtering through Non-negative Matrix Factorization (NMF) and content-based filtering via total variation (TV) on graphs. The graphs encode both playlist proximity information and song similarity, using …

The study uses historical revenue data to forecast music catalog cashflows and multipliers.

In this paper we study deep learning-based music source separation, and explore using an alternative loss to the standard spectrogram pixel-level L2 loss for model training. Our main contribution is in demonstrating that adding a high-level feature loss term, extracted from the spectrograms using a VGG net, can improve…

Detects free group automorphisms using homology of covers.

Minimal surfaces with negative curvature found in large spheres.

Rating prediction is an important application, and a popular research topic in collaborative filtering. However, both the validity of learning algorithms, and the validity of standard testing procedures rest on the assumption that missing ratings are missing at random (MAR). In this paper we present the results of a us…

Study bounds Kähler current diameters on manifolds.

In this paper, we give a criterion for the properness of the K-energy in a general Kahler class of a compact Kahler manifold by using Song-Weinkove's result. As applications, we give some Kahler classes on $\mathbb{C}\mathbb{P}^2\#3\overline {\mathbb{C}\mathbb{P}^2}$ and $\mathbb{C}\mathbb{P}^2\#8\overline {\mathbb{C}\…

We show that the only irreducible three-manifold with positive first Betti number and Heegaard Floer homology of rank two is homeomorphic to zero-framed surgery on the trefoil. We classify links whose branched double cover gives rise to this manifold. Together with a spectral sequence from Khovanov homology to the Floe…

A classical result by Marston Morse asserts that on some ellipsoids of ${\mathbb R}^3$ there exists exactly 3 closed and simple geodesics. The goal of this presentation is to prove that this rigidity result does not extend to higher dimensions and, more precisely, on any smooth closed riemannian manifod of arbitrary di…

Cai, Song and Kou (2015) [Cai, N., Y. Song, S. Kou (2015) A general framework for pricing Asian options under Markov processes. Oper. Res. 63(3): 540-554] made a breakthrough by proposing a general framework for pricing both discretely and continuously monitored Asian options under one-dimensional Markov processes. In …

Music genre classification is a widely researched topic in music information retrieval (MIR). Being able to automatically tag genres will benefit music streaming service providers such as JOOX, Apple Music, and Spotify for their content-based recommendation. However, most studies on music classification have been done …

The paper proves infinitely many free boundary minimal hypersurfaces in compact manifolds.

We study a module structure on Khovanov homology, which we show is natural under the Ozsvath-Szabo spectral sequence to the Floer homology of the branched double cover. As an application, we show that this module structure detects trivial links. A key ingredient of our proof is that the H_1/Torsion module structure on …

It has been suggested in developmental psychology literature that the communication of affect between mothers and their infants correlates with the socioemotional and cognitive development of infants. In this study, we obtained day-long audio recordings of 10 mother-infant pairs in order to study their affect communica…

Jukebox generates high-fidelity songs with singing in raw audio.

The paper solves a 5-manifold foliation problem using a Sasaki-Ricci flow.

Which song will Smith listen to next? Which restaurant will Alice go to tomorrow? Which product will John click next? These applications have in common the prediction of user trajectories that are in a constant state of flux over a hidden network (e.g. website links, geographic location). What users are doing now may b…

Deep learning improves anomaly detection across various fields.

We use virtual knot theory to detect the non-invertibility of some classical links in $\mathbb{S}^3$. These links appear in the study of virtual covers. Briefly, a virtual cover associates a virtual knot $\upsilon$ to a knot $K$ in a $3$-manifold $N$, under certain hypotheses on $K$ and $N$. Virtual covers of links in …

We present five methods to the problem of network anomaly detection. These methods cover most of the common techniques in the anomaly detection field, including Statistical Hypothesis Tests (SHT), Support Vector Machines (SVM) and clustering analysis. We evaluate all methods in a simulated network that consists of nomi…

Empirical evidence suggests link polynomials can detect causality in spacetimes.

New method speeds up neural network training by preprocessing weight-data correlation.

TAnoGan detects anomalies in time series data using GANs.

Researchers study chirality in a specific type of torus-covering link.

We give examples of smooth surfaces with negative first Chern class which are slope unstable with respect to certain polarisations, and so have Kahler classes that do not admit any constant scalar curvature Kahler metrics. We also compare this to the work of Song-Weinkove on the J-flow.

This note explains Ricci flow method for Kähler-Einstein metrics.

We present a novel active learning algorithm for community detection on networks. Our proposed algorithm uses a Maximal Expected Model Change (MEMC) criterion for querying network nodes label assignments. MEMC detects nodes that maximally change the community assignment likelihood model following a query. Our method is…

Researchers prove a Penrose inequality for spacetime with specific conditions.

Probabilistic models often have parameters that can be translated, scaled, permuted, or otherwise transformed without changing the model. These symmetries can lead to strong correlation and multimodality in the posterior distribution over the model's parameters, which can pose challenges both for performing inference a…

Extending ideas of Hedden-Ni, we show that the module structure on Khovanov homology detects split links. We also prove an analogue for untwisted Heegaard Floer homology of the branched double cover. Technical results proved along the way include two interpretations of the module structure on untwisted Heegaard Floer h…

We contribute a pop-song automation framework for lead melody generation and accompaniment arrangement. The framework reflects the major procedures of human music composition, generating both lead melody and piano accompaniment by a unified strategy. Specifically, we take chord progression as an input and propose three…