Dissonance Spectrum explicitly models perceptual frequency interactions for better music understanding

• URL: http://arxiv.org/abs/2608.25621v1
• Date: Wed, 26 Aug 2026 10:42:06 GMT
• Title: Dissonance Spectrum explicitly models perceptual frequency interactions for better music understanding
• Abstract summary: We introduce the emphDance Spectrum (DS) as a nonnegative time-frequency representation that applies a tolerance-based rational pitch-relation kernel with logarithmic harmonic distance to a constant-Q spectrum.<n> Controlled music-theory tests show strong ordinal agreement for intervals, harmonic-function connections, and church modes, and weaker but significant agreement across diverse chord voicings.<n>These results support DS as an interpretable, complementary representation, while listener-specific perception and broader task coverage remain open problems.
• Score: 45.06070631144852
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Conventional music representations describe acoustic energy over time and frequency but do not explicitly expose relations among simultaneous frequency components. We introduce the \emph{Dissonance Spectrum} (DS), a nonnegative time--frequency representation that applies a tolerance-based rational pitch-relation kernel with logarithmic harmonic distance to a constant-Q spectrum and attributes aggregate pairwise interactions back to individual frequency bins. Controlled music-theory tests show strong ordinal agreement for intervals, harmonic-function connections, and church modes, and weaker but significant agreement across diverse chord voicings. DS is then encoded by a lightweight parallel branch whose zero-initialized residual projection preserves the baseline function at initialization. Across six paired training seeds in open-ended music question answering and categorical and dimensional music emotion recognition, DS obtains the highest mean on every reported endpoint relative to the unchanged baseline, a parameter-matched Gaussian-input branch, and an architecture-matched magnitude-CQT branch. These results support DS as an interpretable, complementary representation, while listener-specific perception and broader task coverage remain open problems.

Related papers

• Weaving Light and Time: Unified Harmonic-Geometric Representation Learning for Dense RGB-Event Parsing [55.13802890769086]
  We present Evita, the first unified backbone specifically engineered for dedicated dense RGB-Event parsing.<n>To achieve profound modal synergy, Evita embeds a suite of intrinsic co-learning modules directly into every encoder layer.<n>Evita establishes new state-of-the-art metrics while delivering a superior accuracy-latency trade-off for real-time multimodal perception.
  arXiv  Detail & Related papers  (2026-07-10T06:52:09Z)
• Spatially Distributed Task-Oriented Compression for Multi-Emitter Localization and Characterization with Spectral Overlap [1.4579344926652844]
  Task-oriented distributed compression framework for joint multi-emitter localization and characterization.<n>Experiments on synthetic multi-emitter scenes with spectral overlap show that even extremely compact receiver-side representations can preserve useful information.
  arXiv  Detail & Related papers  (2026-05-31T20:47:30Z)
• TIE: Time Interval Encoding for Video Generation over Events [50.66585165263848]
  Director-style prompting, robotic action prediction, and interactive video agents demand temporal grounding over concurrent events.<n>Modern video generators represent time as discrete points through point-wise positional encodings.<n>Time Interval TIE is a principled, plug-and-play interval-aware generalization.
  arXiv  Detail & Related papers  (2026-05-11T13:23:14Z)
• Sub-Band Spectral Matching with Localized Score Aggregation for Robust Anomalous Sound Detection [11.328862535847785]
  A common training-free anomalous sound detection pipeline temporally pools frame-level representations into a band-preserving feature vector and scores anomalies.<n>A single global neighbor forces all bands to share the same reference, increasing band-level mismatch.<n>We propose BEAM, which stores temporally pooled sub-band vectors in a memory bank, retrieves neighbors per sub-band, and uniformly aggregates scores to reduce normal-score variability and improve discriminability.
  arXiv  Detail & Related papers  (2026-03-14T04:38:41Z)
• Learning to Separate RF Signals Under Uncertainty: Detect-Then-Separate vs. Unified Joint Models [53.79667447811139]
  We show that a single deep neural architecture learns to jointly detect and separate when applied directly to the received signal.<n>These findings highlight UJM as a scalable and practical alternative to DTS, while opening new directions for unified separation under broader estimation.
  arXiv  Detail & Related papers  (2026-02-04T15:25:02Z)
• Interaction as Interference: A Quantum-Inspired Aggregation Approach [4.07636450847048]
  We take a quantum-inspired view of interaction as engineered product terms or as emergent patterns in flexible models.<n>In a minimal linear-amplitude model, this cross-term equals the standard potential-outcome interaction contrast (_mathrmINT) in a factorial design.<n>We instantiate this idea in a lightweight emphInterference Kernel (IKC) and introduce two diagnostics: emphCoherent Gain (log-likelihood gain of coherent over the incoherent proxy) and emphInter
  arXiv  Detail & Related papers  (2025-11-13T06:44:18Z)
• Exploiting Inter-Session Information with Frequency-enhanced Dual-Path Networks for Sequential Recommendation [13.302194364808514]
  We propose FreqRec, a Frequency-Enhanced Dual-Path Network for sequential Recommendation.<n>FreqRec captures inter-session and intra-session behaviors via a learnable Frequency-domain Multi-layer Perceptrons.<n>It is optimized under a composite objective that combines cross entropy with a frequency-domain consistency loss.
  arXiv  Detail & Related papers  (2025-11-09T08:39:26Z)
• Robust Spectral Fuzzy Clustering of Multivariate Time Series with Applications to Electroencephalogram [6.62414474989199]
  We introduce a fuzzy clustering framework in the spectral domain to extract frequency-specific monotonic relationships across variables.<n>Our method takes advantage of dominant frequency-based cross-regional connectivity patterns to improve clustering accuracy.<n>As a flagship application, we analyze electroencephalogram recordings, where our approach uncovers frequency- and connectivity-specific markers of latent cognitive states.
  arXiv  Detail & Related papers  (2025-06-28T12:02:01Z)
• MFRS: A Multi-Frequency Reference Series Approach to Scalable and Accurate Time-Series Forecasting [51.94256702463408]
  Time series predictability is derived from periodic characteristics at different frequencies.<n>We propose a novel time series forecasting method based on multi-frequency reference series correlation analysis.<n> Experiments on major open and synthetic datasets show state-of-the-art performance.
  arXiv  Detail & Related papers  (2025-03-11T11:40:14Z)
• Temporal-Spatial Neural Filter: Direction Informed End-to-End Multi-channel Target Speech Separation [66.46123655365113]
  Target speech separation refers to extracting the target speaker's speech from mixed signals. Two main challenges are the complex acoustic environment and the real-time processing requirement. We propose a temporal-spatial neural filter, which directly estimates the target speech waveform from multi-speaker mixture.
  arXiv  Detail & Related papers  (2020-01-02T11:12:50Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.