comparison README @ 53:bc161fd73858 matthiasm-plugin

made HMM toggle parameter more easily understandable
author matthiasm
date Mon, 25 Oct 2010 19:39:32 +0900
parents 0bf1486dc674
children 0f40aa8b49fa
comparison
equal deleted inserted replaced
52:0bf1486dc674 53:bc161fd73858
43 ### Parameters ### 43 ### Parameters ###
44 44
45 The default settings (in brackets, below) are those used for Matthias Mauch's 2010 MIREX submissions. 45 The default settings (in brackets, below) are those used for Matthias Mauch's 2010 MIREX submissions.
46 46
47 * use approximate transcription (NNLS) (on or off; default: on): toggle between NNLS approximate transcription and linear spectral mapping. 47 * use approximate transcription (NNLS) (on or off; default: on): toggle between NNLS approximate transcription and linear spectral mapping.
48 * Viterbi decoding (on or off; default: on): uses HMM/Viterbi smoothing. Otherwise: heuristic chord change smoothing. 48 * HMM (Viterbi decoding) (on or off; default: on): uses HMM/Viterbi smoothing. Otherwise: heuristic chord change smoothing.
49 * spectral roll on (0.00 -- 0.05; default: 0.0): consider the cumulative energy spectrum (from low to high frequencies). All bins below the first bin whose cumulative energy exceeds [spectral roll on] x [total energy] will be set to 0. A value of 0 means that no bins will be changed. 49 * spectral roll on (0.00 -- 0.05; default: 0.0): consider the cumulative energy spectrum (from low to high frequencies). All bins below the first bin whose cumulative energy exceeds [spectral roll on] x [total energy] will be set to 0. A value of 0 means that no bins will be changed.
50 * tuning mode (global or local; default: global): local uses a local average for tuning, global uses ... exactly. 50 * tuning mode (global or local; default: global): local uses a local average for tuning, global uses ... exactly.
51 * spectral whitening (0.0 -- 1.0; default: 1.0): determines how much the log-frequency spectrum is whitened. A value of 0.0 means no whitening. For values other than 0.0 the log-freq spectral bins are divided by [standard deviation of their neighbours]^[spectral whitening], where "^" means "to the power of". 51 * spectral whitening (0.0 -- 1.0; default: 1.0): determines how much the log-frequency spectrum is whitened. A value of 0.0 means no whitening. For values other than 0.0 the log-freq spectral bins are divided by [standard deviation of their neighbours]^[spectral whitening], where "^" means "to the power of".
52 * spectral shape (0.5 -- 0.9; default: 0.7): the shape of the notes in the NNLS dictionary. Their harmonic amplitude follows a geometrically decreasing pattern, in which the i-th harmonic has an amplitude of [spectral shape]^[i-1], where "^" means "to the power of". 52 * spectral shape (0.5 -- 0.9; default: 0.7): the shape of the notes in the NNLS dictionary. Their harmonic amplitude follows a geometrically decreasing pattern, in which the i-th harmonic has an amplitude of [spectral shape]^[i-1], where "^" means "to the power of".
53 * chroma normalisation (none, maximum norm, L1 norm, L2 norm; default: none): determines whether or how the chromagrams are normalised. If the setting is not 'none', then each chroma frame separately is divided by the chosen vector norm. Note that normalisation implies that the joint 24-dim. "Chroma and Bass Chromagram" output will be different from the individual 12-dim. "Chromagram" and "Bass Chromagram" outputs. 53 * chroma normalisation (none, maximum norm, L1 norm, L2 norm; default: none): determines whether or how the chromagrams are normalised. If the setting is not 'none', then each chroma frame separately is divided by the chosen vector norm. Note that normalisation implies that the joint 24-dim. "Chroma and Bass Chromagram" output will be different from the individual 12-dim. "Chromagram" and "Bass Chromagram" outputs.