bigmerge
b7e2c580a8
El SDK CI - dev / build-and-test (pull_request) Successful in 6m28s
speech.el: formant/glottal integer DSP synthesis + voice-analyze-by-
imitation. voice-profile.el / voice-ingest.el: voice-profile plumbing.
accent.el: British-RP as an ingested transform-geometry (explicitly marked
provisional/citation-pending by its own comments). organ-read.el:
engram read-through for the speech organ. Includes demo/test drivers and
non-personal reference data (British-RP phonetics/lexicon derived data,
a public-domain LibriVox RP reference recording).
Deliberately excludes elp/data/live/ (raw recorded voice + face-photo
samples of the repo owner) and the will-*.{json,psv} derived voiceprint
files — personal biometric data that shouldn't be committed to a shared
repo without an explicit decision from the owner. Also excludes this
worktree's elp/src/surface-profile.el, which diverges from the copy in
other worktrees (agent-aaf04b0a9714c4070, main) — needs manual
reconciliation before landing, left out here to avoid silently picking a
version.
38 lines
2.5 KiB
EmacsLisp
38 lines
2.5 KiB
EmacsLisp
// speech-voicegeom-demo.el - THE JUMP: render Will's VOWEL SPACE + PROSODY
|
|
// (measured over 30s), not the single 11-number average. His vowels land at HIS
|
|
// targets; pitch follows HIS melody. All read back FROM the ingested geometry.
|
|
// INTERIM: the geometry was Python-measured (measure_voice.py, numpy LPC/F0) —
|
|
// to be superseded by the engram-measures-audio path. No source layer.
|
|
|
|
fn main() {
|
|
let outdir: String = "/Users/will/Development/neuron-technologies/foundation/el/.claude/worktrees/agent-acc02900ef4ade35e/elp/tests/examples/out/"
|
|
|
|
// 1: ingest vowel space + prosody as geometry (empty store -> save; set-replace)
|
|
let ig: Int = ingest_voicegeom("elp/data/will-vowelspace.psv", "elp/data/will-prosody.psv", "elp/data/will-voicegeom.engram.json")
|
|
// kf (vocal-tract scale for consonants) from the earlier will-voice manifold
|
|
let sigv: [Int] = load_voice("elp/data/will-voice.engram.json")
|
|
let kf: Int = native_list_get(sigv, 2)
|
|
// 2: read vowel space + prosody back FROM geometry
|
|
let vmap: [String] = load_voicegeom("elp/data/will-voicegeom.engram.json")
|
|
let pros: [Int] = prosody_from(vmap)
|
|
println("[geometry] vowels=" + int_to_str((native_list_len(vmap) - 2) / 2) + " prosody f0_median=" + int_to_str(native_list_get(pros, 0)) + " f0_min=" + int_to_str(native_list_get(pros, 1)) + " f0_max=" + int_to_str(native_list_get(pros, 2)) + " kf=" + int_to_str(kf))
|
|
let ehv: [Int] = vmap_get(vmap, "EH")
|
|
let ihv: [Int] = vmap_get(vmap, "IH")
|
|
println("[his-vowels] EH=" + int_to_str(native_list_get(ehv, 0)) + "/" + int_to_str(native_list_get(ehv, 1)) + " IH=" + int_to_str(native_list_get(ihv, 0)) + "/" + int_to_str(native_list_get(ihv, 1)))
|
|
|
|
// phoneme geometry from the organ (loaded AFTER caches are in EL)
|
|
let pmap: [String] = organ_pmap("elp/data/phonetics-formants.engram.json")
|
|
let lmap: [String] = organ_lex("elp/data/lexicon.psv")
|
|
|
|
// 3+4: render FROM MEANING in his-vowels + his-prosody voice
|
|
let vw: [String] = voice_will(native_list_get(pros, 0), native_list_get(pros, 1), kf)
|
|
let noacc: [String] = native_list_empty()
|
|
let novset: [String] = native_list_empty()
|
|
let t: String = sem_realize(sem_frame("greet", "Will", "", ""))
|
|
let codes: [String] = text_phonemes(lmap, t)
|
|
println("[render] \"" + t + "\" :: " + list_join(codes, " "))
|
|
let samples: [Int] = synth_codes_accent(codes, vw, pmap, noacc, novset, vmap, pros)
|
|
let ok: Bool = write_wav(samples, 16000, outdir + "will-reply3.wav")
|
|
println("[done] will-reply3.wav=" + bool_to_str(ok))
|
|
}
|