Music arousal changes forecasted from scheduled future music chunks
Known Music, Unknown Response: Leakage-Audited Dynamic Arousal Forecasting With Scheduled Future Music
Sound
Summary
This paper looks at predicting how listeners' feelings of excitement or calmness (arousal) will change when they hear upcoming pieces of music. Unlike traditional methods that analyze music already played, the authors focus on forecasting changes based on short future music segments, even without knowing listeners' future reactions. Their approach shows that just knowing the upcoming music and its position within a song helps predict emotional changes better than some existing models. They also carefully design their method to avoid leaking future information that would make the predictions unrealistic.
What this means in practice
- •For music streaming services: Predict listener emotional responses to upcoming songs to improve playlist sequencing and personalized music recommendations.$Commercial implications: Supports real-time adjustment of playlists for emotional impact, creating valuable user engagement features in streaming platforms.
- •For interactive entertainment developers: Use scheduled future music segments to anticipate player or audience arousal changes in gaming or live shows.
Authors
Bin Wen, Dai-Qiao Zhang, Tien-Ping Tan
Abstract
Dynamic music emotion recognition usually estimates concurrent or lag-aligned labels from audio that has already been observed. We instead forecast the change in consensus arousal when the upcoming music is scheduled but all later affect labels remain hidden. Evaluation holds out complete songs, encodes each eligible 4-s chunk independently, predicts arousal innovation, and compares the correct future with displaced segments from the same song. On PMEmo and a 1,494-song DEAM evaluation pool excluded from engineering development, a complete past/future MuQ representation raises concordance correlation coefficient (CCC) by 0.389--0.507 over recent affect and remains 0.268--0.382 above a calibrated nonlinear state model. A future-only trajectory contains no past or current audio and still exceeds that state model by 0.150--0.249. The earliest legal future chunk, which ends 5.5--11 s before the target, also remains informative. Correct placement exceeds an overlapping 5-s shift by 0.100--0.209 and the acoustic-nearest eligible same-song segment by 0.078--0.105, with positive song-cluster lower bounds. These results show that both scheduled content and its within-song position carry forecast information under the stated observation rules. The study provides a leakage-controlled reference for known-future music forecasting without treating predictive substitutions as causal interventions.