This study addresses the prediction of audio popularity on an online sharing platform by leveraging both metadata and acoustic feature representations. Two distinct categories of audio content are considered: music and sound effects. Popularity is formulated as a supervised classification task based on two target variables: the number of downloads and the average user rating. We conduct a comparative evaluation of multiple machine learning models, including Random Forest, XGBoost, and a Neural Network model. Experiments are performed across different feature sets, including metadata, platform-provided descriptors, and eGeMAPS acoustic features. Results indicate that metadata consistently provide the most informative representation for predicting popularity. Nevertheless, acoustic features alone achieve performance significantly above chance level, demonstrating that intrinsic properties of the audio signal contribute to popularity prediction.
Figures & tables
SE
Mu
Train (80%)
13,963
14,340
Test (20%)
3,491
3,586
Table 1: Number of files in Train and Test splits. Ratios represent the proportion of data kept in a given split from the original dataset. Both sets are disjoint.
Target
Avg-Rat.
#Down.
Dataset
Model
MLP
RandomForest
XGBoost
MLP
RandomForest
XGBoost
Mu
Acu-FS
0.441 ± 0.005
0.562 ± 0.010
0.640 ± 0.014
0.586 ± 0.019
0.644 ± 0.012
0.657 ± 0.010
eGeMAPS
0.407 ± 0.008
0.410 ± 0.009
0.414 ± 0.010
0.568 ± 0.008
0.601 ± 0.008
0.594 ± 0.006
MERT
0.303 ± 0.011
0.313 ± 0.011
0.315 ± 0.013
0.461 ± 0.006
0.489 ± 0.012
0.479 ± 0.008
Metadata
0.411 ± 0.015
0.472 ± 0.015
0.510 ± 0.017
0.623 ± 0.006
0.732 ± 0.004
0.735 ± 0.005
SE
Acu-FS
0.238 ± 0.012
0.487 ± 0.010
0.572 ± 0.019
0.550 ± 0.016
0.706 ± 0.003
0.720 ± 0.005
Table 2: Classification performance F1-score ( ± 95% CI). Bold values indicate the best model and underlined values the second best.
Music popularity prediction has attracted growing research interest, with relevance to artists, platforms, and recommendation systems. However, the explosive rise of AI-generated music platforms has created an entirely new and largely unexplored landscape, where a surge of songs is produced and consumed daily without the traditional markers of artist reputation or label backing. Key, yet unexplored in this pursuit is aesthetic quality. We propose APEX, the first large-scale multi-task learning framework for AI-generated music, trained on over 211k songs (10k hours of audio) from Suno and Udio, that jointly predicts engagement-based popularity signals - streams and likes scores - alongside five perceptual aesthetic quality dimensions from frozen audio embeddings extracted from MERT, a self-supervised music understanding model. Aesthetic quality and popularity capture complementary aspects of music that together prove valuable: in an out-of-distribution evaluation on the Music Arena dataset, comprising pairwise human preference battles across eleven generative music systems unseen during training, including aesthetic features consistently improves preference prediction, demonstrating strong generalisation of the learned representations across generative architectures.
Jaavid Aktar Husain, Dorien Herremans
AMAAI Lab, Singapore University of Technology and Design
Narration is central to the audiobook listening experience, shaping how listeners engage with and understand the content. This work explores how narration qualities shape an audiobook's appeal, noting that their effects can vary by genre, title, and audience. We extract vocal and acoustic features (e.g., tone, pace, loudness) from LibriVox using pre-trained audio models and analyse their relationship with consumption data (specifically, view-rate) and their interplay with genre and title. Despite limited consumption data, we find that acoustic information alone has a robust association with appeal, even after accounting for title effects. We further validate these findings using more nuanced proprietary engagement metrics. To our knowledge, this is the first systematic computational study linking narration qualities, genre, title, and audiobook consumption, highlighting the potential of data-driven insights to improve audiobook personalisation and narrator casting.
Shahar Elisha, Mariano Beguerisse-Díaz, Emmanouil Benetos
Crossmodal correspondences between sound and taste are well established in psychology and neuroscience, but largely absent from content-based multimedia retrieval. We formalise taste-from-audio prediction as a content-based music information retrieval benchmark over a perceptually validated multi-source corpus, comparing ten frozen audio encoders from the four HEAR families under a shared multi-task regression head, with gated late-fusion as a configurable variant. In order to assess the effectiveness of the models, we compute absolute error and rank correlation. The strongest systems predict the five tastes within a macro RMSE of 0.134; on held-out real music their error is less than half a single rater's deviation from the consensus (RMSE 0.13 vs. 0.28), so the model tracks the group consensus more closely than an average human rater, and well below the previous state of the art baseline (0.219). On absolute error the encoders are statistically flat, with a single VGGish matching the best fusion, but gated late-fusion's advantage is confined to rank correlation (macro Pearson r 0.724 vs. 0.666). Operationalised as a content-based retrieval index, the predicted taste space ranks a 309-item pool far more faithfully than a CLAP-text baseline, which sits at chance; ridge probes and an audio-bandstop knockout read the strongest representations against documented sound-taste correspondences.