owenandClaude Sonnet 5
b6acd63c2d
Adds internal/audiofeatures: decodes each scanned song to PCM via ffmpeg and computes actual measured characteristics — tempo (via autocorrelation of the frame energy envelope, left unset rather than guessed when a clip is too short to contain a beat), an approximate loudness figure, spectral centroid/rolloff and zero-crossing rate (via a hand-written FFT), and a 12-bin chroma vector used both for a Krumhansl-Kessler key estimate and as similarity-index input. No external DSP/ML dependency. The scanner now runs this analysis after indexing each song (as part of the already-background scan, not on any request path) and stores results in the existing audio_features table via the new database.UpsertAudioFeatures/GetAudioFeatures/ListAllAudioFeatures. internal/similarity is a small in-process nearest-neighbor index: z-score normalizes each feature dimension across the analyzed library and answers Nearest (ranked real distances) and Path (a feature-space straight-line walk from one track to another, hopping to the closest not-yet-used real song at each step — never a fabricated intermediate track). getSonicSimilarTracks and findSonicPath expose these through the standard sonicMatch response, converting distance to a normalized (0,1] similarity score. A song that hasn't been analyzed yet is simply absent from results rather than faked. Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_014r98AtcBbevpscWLsfwVvv
66 lines
1.5 KiB
Go
66 lines
1.5 KiB
Go
package audiofeatures
|
|
|
|
import "math"
|
|
|
|
// fft computes the in-place iterative radix-2 Cooley-Tukey FFT of a,
|
|
// whose length must be a power of two. It's the only DSP primitive this
|
|
// package needs (spectral centroid/rolloff and the chroma vector all
|
|
// derive from the resulting magnitude spectrum), so a small
|
|
// hand-written implementation avoids pulling in an external numerics
|
|
// dependency for one function.
|
|
func fft(a []complex128) {
|
|
n := len(a)
|
|
if n <= 1 {
|
|
return
|
|
}
|
|
|
|
// Bit-reversal permutation.
|
|
for i, j := 1, 0; i < n; i++ {
|
|
bit := n >> 1
|
|
for ; j&bit != 0; bit >>= 1 {
|
|
j ^= bit
|
|
}
|
|
j ^= bit
|
|
if i < j {
|
|
a[i], a[j] = a[j], a[i]
|
|
}
|
|
}
|
|
|
|
for length := 2; length <= n; length <<= 1 {
|
|
ang := -2 * math.Pi / float64(length)
|
|
wlen := complex(math.Cos(ang), math.Sin(ang))
|
|
for i := 0; i < n; i += length {
|
|
w := complex(1, 0)
|
|
half := length / 2
|
|
for k := 0; k < half; k++ {
|
|
u := a[i+k]
|
|
v := a[i+k+half] * w
|
|
a[i+k] = u + v
|
|
a[i+k+half] = u - v
|
|
w *= wlen
|
|
}
|
|
}
|
|
}
|
|
}
|
|
|
|
// magnitudeSpectrum returns |FFT(frame)| for bins [0, n/2], given a
|
|
// real-valued frame whose length is a power of two.
|
|
func magnitudeSpectrum(frame []float64) []float64 {
|
|
n := len(frame)
|
|
buf := make([]complex128, n)
|
|
for i, v := range frame {
|
|
buf[i] = complex(v, 0)
|
|
}
|
|
fft(buf)
|
|
mags := make([]float64, n/2+1)
|
|
for i := range mags {
|
|
mags[i] = cmplxAbs(buf[i])
|
|
}
|
|
return mags
|
|
}
|
|
|
|
func cmplxAbs(c complex128) float64 {
|
|
re, im := real(c), imag(c)
|
|
return math.Sqrt(re*re + im*im)
|
|
}
|