Chroma features are a digital audio representation that projects a signal's spectral energy onto the 12 pitch classes of the Western equal-tempered scale, producing a 12-dimensional vector invariant under octave transposition. The representation is carved by (1) the 12-tone chromatic partition, (2) the octave-invariance constraint, and (3) the spectral projection operation that folds frequency bins onto pitch-class bins. It persists in audio analysis software, music information retrieval systems, and symbolic representations of tonal harmony. [formal: chroma | substrate: mind | horizon: hours | explicit: yes | epoch: 0.41]
Accepted ontology entry
chroma-features
Chroma features are a digital audio representation that projects a signal's spectral energy onto the 12 pitch classes of the Western equal-tempered scale, producing a 12-dimensional vector invariant under octave transposition. The represen…
Definition
Why it is in scope
Chroma features are a human-made audio representation that captures the distribution of spectral energy across the 12 pitch classes of the Western equal-tempered scale, independent of octave. They are computed by projecting a time-frequency representation onto pitch-class kernels and serve as a fundamental building block for music information retrieval systems including chord recognition, key detection, and music similarity matching.
Names and aliases
- chroma-featuresen · CANONICAL
Relations from this entry
- cmsqymxwg002gswynqd32ljccDEPENDS_ON →
Chroma features operate by folding spectral energy onto pitch-class bins. Remove the pitch-class concept and the projection has no target — chroma features stop operating entirely. This is not meta-level (they need naming); the pitch-class partition is the structural skeleton of the representation itself.
- cmsq4obya07m0jlssh92wv3v0DEPENDS_ON →
Chroma features operate by projecting a signal's spectral representation onto pitch-class bins. Remove spectral-representation as input and chroma-features have no data to operate on — the projection target is the spectral energy distribution, which IS a spectral representation. This is a present-tense constitutive dependency.
- cmspqj6jh0677jlssnhgl6v8dDEPENDS_ON →
Chroma features are computed by folding the magnitude spectrum into 12 pitch classes. Remove magnitude-spectrum and chroma extraction has no spectral input to fold. The removal test passes.
- cmsrrpmnd0004h7yu0m6ty8g1SERVES →
Chroma features are designed and maintained for the sake of music information retrieval: capturing pitch-class distributions is fundamental to MIR tasks like chord recognition, melody extraction, and music similarity. Its designed purpose is to further MIR's operation.
- cmsqglbgv00763e32jisx8hz3INSTANCE_OF →
Chroma features are a specific kind of spectral feature — they encode spectral energy distribution across 12 pitch classes. A competent speaker would call chroma features 'a spectral feature.' Files against nearest accepted kind.
- cmspxgu9f06vtjlssp8aaz07zDEPENDS_ON →
Chroma feature extraction operates by applying a mel-scale filterbank to the magnitude spectrum, then folding into pitch classes. The mel filterbank is the constitutive mechanism — remove it and chroma features cannot be computed as defined. Present-tense removal test passes.
Relations to this entry
- cmsrep44o017mkp53qzi49sa1← DEPENDS_ON
Pitch-class profile (PCP) encodes the energy distribution across the 12 pitch classes, computed directly from chroma features. Removal test: remove chroma-features and PCP has no representation to compute from. Constitutive dependency.
Record identity
- Created
- Aug 13, 2026, 2:55 PM UTC
- Content hash
- 9bb06ad18ee5f54a7072aa84355ffbbd24f912fa7a538564311e8a74df278b79