Add native speech synthesis and voice-imitation faculty

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.

elp/tests/examples/speech-accent-demo.el

@@ -0,0 +1,45 @@
+// speech-accent-demo.el - PROOF: Neuron speaks with a BRITISH accent, where the
+// accent is a TRANSFORM composed onto the voice (voice (+) accent, separable),
+// INGESTED as geometry (not a table). Same voice, accent toggled on/off = RP/GA.
+
+fn main() {
+    let outdir: String = "/Users/will/Development/neuron-technologies/foundation/el/.claude/worktrees/agent-acc02900ef4ade35e/elp/tests/examples/out/"
+
+    // LEARN: base phonetics + lexicon + the British-RP accent transform, all as
+    // ingested geometry (source -> manifold -> engram).
+    let pmap: [String] = ingest_phonetics("elp/data/phonetics.psv")
+    let lmap: [String] = ingest_lexicon("elp/data/lexicon.psv")
+    let amap: [String] = ingest_accent("elp/data/british-accent.psv")
+    println("[learn] phonemes=" + int_to_str(native_list_len(pmap) / 2) + " words=" + int_to_str(native_list_len(lmap) / 2) + " accent_targets=" + int_to_str(native_list_len(amap) / 2))
+
+    let neuron: [String] = voice_neuron()
+    let noaccent: [String] = native_list_empty()
+
+    // -- Sentence 1: "I am Neuron." from meaning ----------------------------
+    let fr1: [String] = sem_frame("describe", "I", "Neuron", "")
+    let t1: String = sem_realize(fr1)
+    let c1: [String] = text_phonemes(lmap, t1)
+    println("[s1] " + t1 + " :: " + list_join(c1, " "))
+
+    // separability: SAME voice, accent OFF (GA) vs ON (RP)
+    let ga: [Int] = synth_codes_accent(c1, neuron, pmap, noaccent)
+    let okga: Bool = write_wav(ga, 16000, outdir + "ga-neuron.wav")
+    let br1: [Int] = synth_codes_accent(c1, neuron, pmap, amap)
+    let okb1: Bool = write_wav(br1, 16000, outdir + "british-neuron.wav")
+
+    // -- Sentence 2: showcases NON-RHOTICITY --------------------------------
+    let fr2: [String] = sem_frame("describe", "I", "here", "")
+    let t2: String = sem_realize(fr2)
+    let c2: [String] = text_phonemes(lmap, t2)
+    let c2rp: [String] = apply_rhoticity(c2, pmap)
+    println("[s2] " + t2 + " :: GA=" + list_join(c2, " ") + "  RP=" + list_join(c2rp, " "))
+    let br2: [Int] = synth_codes_accent(c2, neuron, pmap, amap)
+    let okb2: Bool = write_wav(br2, 16000, outdir + "british-2.wav")
+
+    // show an RP override read straight from the accent geometry
+    let ovAA: [Int] = accent_formants(amap, "AA")
+    if native_list_len(ovAA) >= 3 {
+        println("[accent-geometry] AA(LOT) RP f1=" + int_to_str(native_list_get(ovAA, 0)) + " f2=" + int_to_str(native_list_get(ovAA, 1)) + " (base GA 730/1090) [PROVISIONAL]")
+    }
+    println("[done] ga-neuron=" + bool_to_str(okga) + " british-neuron=" + bool_to_str(okb1) + " british-2=" + bool_to_str(okb2))
+}

elp/tests/examples/speech-demo.el

@@ -0,0 +1,69 @@
+// speech-demo.el - PROOF: Neuron speaks from MEANING, rendered through INGESTED
+// phonetic geometry, own-core, plus voice-by-IMITATION. Built by concatenating
+// the elp realizer + voice-profile + speech-ingest + speech, then this main.
+//
+//   LEARN   : ingest acoustic-phonetics + lexicon SOURCES -> phoneme manifold in
+//             the engram (source -> manifold -> merge).
+//   MEANING : sem_frame("describe","I","Neuron","") -> sem_realize -> "I am Neuron."
+//   PHONES  : words -> phoneme codes, READ from the ingested lexicon geometry.
+//   RENDER  : superpose formant resonances (read from engram) over a glottal
+//             source -> own-core PCM/WAV, in Neuron's own voice.
+//   IMITATE : HEAR a short sample of a different voice -> extract its signature
+//             by ear (autocorrelation pitch + integer-DFT formant) -> render new
+//             speech in that voice. An impression, not a corpus.
+
+fn speak_report(tag: String, codes: [String], voice: [String], pmap: [String], path: String) -> [Int] {
+    let s: [Int] = synth_codes(codes, voice, pmap)
+    let ok: Bool = write_wav(s, 16000, path)
+    println(tag + " samples=" + int_to_str(native_list_len(s)) + " ok=" + bool_to_str(ok) + " -> " + path)
+    return s
+}
+
+fn main() {
+    let outdir: String = "/private/tmp/claude-501/-Users-will/6531446d-bc27-4095-930b-e04777c3db4f/scratchpad/"
+
+    // -- LEARN: ingest the speech primitives as geometry --------------------
+    let pmap: [String] = ingest_phonetics("elp/data/phonetics.psv")
+    let lmap: [String] = ingest_lexicon("elp/data/lexicon.psv")
+    let saved: Bool = engram_save(outdir + "phoneme-manifold.json")
+    println("[learn] phonemes=" + int_to_str(native_list_len(pmap) / 2) + " words=" + int_to_str(native_list_len(lmap) / 2) + " manifold_saved=" + bool_to_str(saved))
+
+    // sanity: show that AA's formants came from ingested geometry, not code
+    let aa: [Int] = phon_geo(pmap, "AA")
+    let aaF1: Int = native_list_get(aa, 0)
+    let aaF2: Int = native_list_get(aa, 1)
+    println("[read-geometry] AA F1=" + int_to_str(aaF1) + " F2=" + int_to_str(aaF2) + " (parsed from engram node)")
+
+    // -- MEANING -> WORDS via the realizer's language faculty ----------------
+    let frame: [String] = sem_frame("describe", "I", "Neuron", "")
+    let text: String = sem_realize(frame)
+    println("[meaning->text] " + text)
+
+    // -- WORDS -> PHONEMES (read from ingested lexicon geometry) --------------
+    let codes: [String] = text_phonemes(lmap, text)
+    println("[phonemes] " + list_join(codes, " "))
+
+    // -- RENDER in Neuron's own voice ----------------------------------------
+    let neuron: [String] = voice_neuron()
+    let s1: [Int] = speak_report("[speak neuron]", codes, neuron, pmap, outdir + "neuron.wav")
+
+    // -- IMITATION: hear a distinct voice, recover its signature, re-render ---
+    let vA: [String] = voice_target_a()
+    let hcodes: [String] = native_list_empty()
+    hcodes = native_list_append(hcodes, "SIL")
+    let z: Int = 0
+    while z < 6 {
+        hcodes = native_list_append(hcodes, "AA")
+        z = z + 1
+    }
+    hcodes = native_list_append(hcodes, "SIL")
+    let heard: [Int] = synth_codes(hcodes, vA, pmap)
+    let okh: Bool = write_wav(heard, 16000, outdir + "heard.wav")
+
+    let vB: [String] = voice_analyze(heard, 16000)
+    println("[imitate] heard ACTUAL   f0=" + voice_get(vA, "f0") + " kf=" + voice_get(vA, "kf"))
+    println("[imitate] heard RECOVERED f0=" + voice_get(vB, "f0") + " kf=" + voice_get(vB, "kf") + " (extracted by ear from PCM)")
+    let s2: [Int] = speak_report("[speak imitation]", codes, vB, pmap, outdir + "imitation.wav")
+
+    println("[done] rendered from meaning + ingested geometry; imitation from a heard sample.")
+}

elp/tests/examples/speech-organ-demo.el

@@ -0,0 +1,48 @@
+// speech-organ-demo.el - PROOF: the render now reads its phoneme + accent
+// GEOMETRY from the ingest ORGAN's saved engram files (engram_load +
+// engram_scan_nodes_json + cache), not a same-run hand-load. The British accent
+// is still a composed transform-geometry (voice (+) accent, separable). Numbers
+// come from the organ manifold; the .psv supplies only categorical vowel-class.
+
+fn main() {
+    let outdir: String = "/Users/will/Development/neuron-technologies/foundation/el/.claude/worktrees/agent-acc02900ef4ade35e/elp/tests/examples/out/"
+
+    // engram-independent caches from source (survive engram_load replacement)
+    let vset: [String] = organ_vset("elp/data/phonetics.psv")
+    let lmap: [String] = organ_lex("elp/data/lexicon.psv")
+    // ORGAN read: phonetics FIRST (cache), THEN accent (engram_load replaces store)
+    let pmap: [String] = organ_pmap("elp/data/phonetics-formants.engram.json")
+    let amap: [String] = organ_amap("elp/data/british-accent.engram.json")
+    println("[organ] phon_syms=" + int_to_str(native_list_len(pmap) / 2) + " accent_syms=" + int_to_str(native_list_len(amap) / 2) + " vowels=" + int_to_str(native_list_len(vset)) + " words=" + int_to_str(native_list_len(lmap) / 2))
+
+    // prove the numbers came from the organ node content
+    let g: [Int] = phon_geo(pmap, "AA")
+    println("[organ-read] phoneme AA f1=" + int_to_str(native_list_get(g, 0)) + " f2=" + int_to_str(native_list_get(g, 1)) + " f3=" + int_to_str(native_list_get(g, 2)) + " (P&B1952 MEASURED)")
+    let ov: [Int] = accent_formants(amap, "AA")
+    if native_list_len(ov) >= 3 {
+        println("[organ-read] accent AA(LOT) f1=" + int_to_str(native_list_get(ov, 0)) + " f2=" + int_to_str(native_list_get(ov, 1)) + " (DERIVED RP, PROVISIONAL)")
+    }
+    println("[organ-read] non_rhotic=" + int_to_str(is_nonrhotic(amap)))
+
+    let neuron: [String] = voice_neuron()
+    let noacc: [String] = native_list_empty()
+
+    // Sentence 1: "I am Neuron." from meaning; GA vs RP = separable toggle
+    let t1: String = sem_realize(sem_frame("describe", "I", "Neuron", ""))
+    let c1: [String] = text_phonemes(lmap, t1)
+    println("[s1] " + t1 + " :: " + list_join(c1, " "))
+    let ga: [Int] = synth_codes_accent(c1, neuron, pmap, noacc, vset)
+    let okga: Bool = write_wav(ga, 16000, outdir + "ga-neuron-organ.wav")
+    let br1: [Int] = synth_codes_accent(c1, neuron, pmap, amap, vset)
+    let okb1: Bool = write_wav(br1, 16000, outdir + "british-neuron-organ.wav")
+
+    // Sentence 2: non-rhoticity showcase
+    let t2: String = sem_realize(sem_frame("describe", "I", "here", ""))
+    let c2: [String] = text_phonemes(lmap, t2)
+    let c2rp: [String] = apply_rhoticity(c2, vset)
+    println("[s2] " + t2 + " :: GA=" + list_join(c2, " ") + "  RP=" + list_join(c2rp, " "))
+    let br2: [Int] = synth_codes_accent(c2, neuron, pmap, amap, vset)
+    let okb2: Bool = write_wav(br2, 16000, outdir + "british-2-organ.wav")
+
+    println("[done] ga-organ=" + bool_to_str(okga) + " british-organ=" + bool_to_str(okb1) + " british-2-organ=" + bool_to_str(okb2))
+}

elp/tests/examples/speech-voice-demo.el

@@ -0,0 +1,31 @@
+// 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))
+}

elp/tests/examples/speech-voice-demo2.el

@@ -0,0 +1,48 @@
+// speech-voice-demo2.el - LIVE VOICE LOOP on Will's richer 30s read, with a
+// GEOMETRIC SET-REPLACE of the voice_will manifold (supersede the coarse 10s
+// region, insert the 30s region — no duplicate node, no per-node CRUD; Will's
+// standing rule f999c5ff). HONEST: 30s steadies the 11-number average over more
+// of his vowels, but it is still one formant triple with no coarticulation or
+// prosody — closer but still synthetic, 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/will30-voiceprint.json"
+    let manifest: String = "elp/data/will-voice.engram.json"
+
+    // --- SET-REPLACE step 1: read the PRIOR region (text read of the manifold
+    //     file — no engram_load, so the store stays clean) and report what is
+    //     being superseded. ---
+    let prior: String = fs_read(manifest)
+    let pp: Int = str_index_of(prior, "voice will ")
+    if pp >= 0 {
+        let pw: String = str_slice(prior, pp, pp + 200)
+        println("[set-replace] superseding PRIOR voice region: f0=" + int_to_str(parse_uint_from(pw, "f0=")) + " kf=" + int_to_str(parse_uint_from(pw, "kf=")) + " f1=" + int_to_str(parse_uint_from(pw, "f1=")))
+    }
+
+    // --- step 2: reshape the 30s voiceprint -> organ voice-signature source ---
+    let sig: [Int] = reshape_voiceprint(vp, "elp/data/will-voice.json")
+
+    // --- step 3: INSERT the fresh 30s region into an EMPTY engram and save ->
+    //     wholesale replaces the manifold file (old region dropped, not edited,
+    //     not duplicated). This is the geometric set-replace. ---
+    let ig: Int = ingest_voice(sig, manifest)
+
+    // --- step 4: READ the new target BACK from geometry ---
+    let g: [Int] = load_voice(manifest)
+    println("[voice-geometry] new region 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 30s, COARSE — not a clone)")
+
+    // phoneme + lexicon geometry from the organ (loaded after the voice sig is
+    // cached in EL, since engram_load replaces the store)
+    let pmap: [String] = organ_pmap("elp/data/phonetics-formants.engram.json")
+    let lmap: [String] = organ_lex("elp/data/lexicon.psv")
+
+    // --- step 5: render a fresh reply FROM MEANING in the 30s Will 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-reply2.wav")
+    println("[done] will-reply2.wav=" + bool_to_str(ok))
+}

elp/tests/examples/speech-voicegeom-demo.el

@@ -0,0 +1,37 @@
+// 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))
+}