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.
32 lines
2.2 KiB
EmacsLisp
32 lines
2.2 KiB
EmacsLisp
// speech-voice-demo.el - LIVE VOICE LOOP (stand-in test). Capture -> voiceprint
|
|
// -> reshape -> INGEST AS GEOMETRY -> read the target back FROM geometry -> the
|
|
// EL projector renders a line reaching for that voice. Stand-in "Will" = the
|
|
// voiceprint of imitation.wav. HONEST: pitch + coarse vocal-tract scale, NOT a clone.
|
|
|
|
fn main() {
|
|
let outdir: String = "/Users/will/Development/neuron-technologies/foundation/el/.claude/worktrees/agent-acc02900ef4ade35e/elp/tests/examples/out/"
|
|
let vp: String = "/private/tmp/claude-501/-Users-will/6531446d-bc27-4095-930b-e04777c3db4f/scratchpad/will-voiceprint.json"
|
|
|
|
// 1+2: reshape voiceprint JSON -> organ voice-signature source
|
|
let sig0: [String] = native_list_empty()
|
|
let sig: [Int] = reshape_voiceprint(vp, "elp/data/will-voice.json")
|
|
// 3: ingest as geometry + engram_save a reloadable manifold file
|
|
let ig: Int = ingest_voice(sig, "elp/data/will-voice.engram.json")
|
|
// 4: READ the target back FROM geometry (engram_load + scan + filter)
|
|
let g: [Int] = load_voice("elp/data/will-voice.engram.json")
|
|
println("[voice-geometry] read from manifold: f0=" + int_to_str(native_list_get(g, 0)) + " f0_end=" + int_to_str(native_list_get(g, 1)) + " kf=" + int_to_str(native_list_get(g, 2)) + " f1=" + int_to_str(native_list_get(g, 3)) + " f2=" + int_to_str(native_list_get(g, 4)) + " f3=" + int_to_str(native_list_get(g, 5)) + " (measured, COARSE — not a clone)")
|
|
|
|
// phoneme geometry from the organ (loaded AFTER the voice sig is cached in EL)
|
|
let pmap: [String] = organ_pmap("elp/data/phonetics-formants.engram.json")
|
|
let lmap: [String] = organ_lex("elp/data/lexicon.psv")
|
|
|
|
// 5: render a line FROM MEANING in Will's voice
|
|
let vw: [String] = voice_will(native_list_get(g, 0), native_list_get(g, 1), native_list_get(g, 2))
|
|
let t: String = sem_realize(sem_frame("greet", "Will", "", ""))
|
|
let codes: [String] = text_phonemes(lmap, t)
|
|
println("[render] \"" + t + "\" :: " + list_join(codes, " ") + " in voice=will f0=" + int_to_str(voice_get_int(vw, "f0")) + " kf=" + int_to_str(voice_get_int(vw, "kf")))
|
|
let samples: [Int] = synth_codes(codes, vw, pmap)
|
|
let ok: Bool = write_wav(samples, 16000, outdir + "will-reply.wav")
|
|
println("[done] will-reply.wav=" + bool_to_str(ok))
|
|
}
|