el/elp/src/speech.el

// speech.el - The native SPEECH render path + voice-by-imitation extractor.
//
// Speech = the AUDIO surface (surface_profile_audio) rendering LANGUAGE-meaning
// through a VOICE signature. The realizer's language faculty supplies the words
// (meaning -> sem_realize -> text); this module turns text -> phonemes (phonetics.el)
// -> a formant-target track over time -> SUPERPOSES formant resonances over a
// glottal source (own-core formant synthesis, the exact integer mirror of the
// music additive superpose) -> own-core PCM/WAV. Two paths:
//   (1) RENDER:  speak(text, voice) -> spoken WAV.
//   (2) IMITATE: voice_analyze(pcm) -> a voice signature grabbed BY EAR
//                (autocorrelation pitch + integer-DFT formant peaks), then render
//                any new meaning in that voice. An impression, not a corpus.
// All integer/fixed-point (EL float arithmetic is unusable).

// -- Own-core integer sine (Bhaskara I), phase 0..65535 = one cycle -----------
fn sp_sin(phase: Int) -> Int {
    let deg: Int = phase * 360 / 65536
    let neg: Int = 0
    if deg > 180 {
        deg = deg - 180
        neg = 1
    }
    let t: Int = deg * (180 - deg)
    let num: Int = 32767 * 4 * t
    let den: Int = 40500 - t
    let v: Int = num / den
    if neg == 1 {
        v = 0 - v
    }
    return v
}

fn sp_cos(phase: Int) -> Int {
    let p: Int = phase + 16384
    p = p - (p / 65536) * 65536
    return sp_sin(p)
}

// One formant resonance (Lorentzian peak), Q15. Peak 32767 at f=fc.
fn sp_gain(f: Int, fc: Int, bw: Int) -> Int {
    let d: Int = f - fc
    let den: Int = d * d + bw * bw
    let num: Int = 32767 * bw * bw
    return num / den
}

fn sp_isqrt(n: Int) -> Int {
    if n <= 0 {
        return 0
    }
    let x: Int = n
    let y: Int = (x + 1) / 2
    while y < x {
        x = y
        y = (x + n / x) / 2
    }
    return x
}

// -- WAV serializer (thin medium; the only non-DSP glue) ---------------------
fn wav_le16(buf: String, off: Int, v: Int) -> String {
    let u: Int = v
    if u < 0 {
        u = u + 65536
    }
    let lo: Int = u - (u / 256) * 256
    let hi: Int = u / 256
    let b: String = __str_set_char(buf, off, lo)
    b = __str_set_char(b, off + 1, hi)
    return b
}

fn wav_le32(buf: String, off: Int, v: Int) -> String {
    let b0: Int = v - (v / 256) * 256
    let r1: Int = v / 256
    let b1: Int = r1 - (r1 / 256) * 256
    let r2: Int = r1 / 256
    let b2: Int = r2 - (r2 / 256) * 256
    let b3: Int = r2 / 256
    let b: String = __str_set_char(buf, off, b0)
    b = __str_set_char(b, off + 1, b1)
    b = __str_set_char(b, off + 2, b2)
    b = __str_set_char(b, off + 3, b3)
    return b
}

fn wav_ascii(buf: String, off: Int, s: String) -> String {
    let n: Int = str_len(s)
    let i: Int = 0
    let b: String = buf
    while i < n {
        let c: Int = str_char_code(s, i)
        b = __str_set_char(b, off + i, c)
        i = i + 1
    }
    return b
}

fn write_wav(samples: [Int], sr: Int, path: String) -> Bool {
    let ns: Int = native_list_len(samples)
    let datalen: Int = ns * 2
    let total: Int = 44 + datalen
    let buf: String = __str_alloc(total)
    buf = wav_ascii(buf, 0, "RIFF")
    buf = wav_le32(buf, 4, 36 + datalen)
    buf = wav_ascii(buf, 8, "WAVE")
    buf = wav_ascii(buf, 12, "fmt ")
    buf = wav_le32(buf, 16, 16)
    buf = wav_le16(buf, 20, 1)
    buf = wav_le16(buf, 22, 1)
    buf = wav_le32(buf, 24, sr)
    buf = wav_le32(buf, 28, sr * 2)
    buf = wav_le16(buf, 32, 2)
    buf = wav_le16(buf, 34, 16)
    buf = wav_ascii(buf, 36, "data")
    buf = wav_le32(buf, 40, datalen)
    let j: Int = 0
    let off: Int = 44
    while j < ns {
        let raw: Int = native_list_get(samples, j)
        buf = wav_le16(buf, off, raw)
        off = off + 2
        j = j + 1
    }
    return __fs_write_bytes(path, buf, total)
}

// One formant resonance as a float Lorentzian peak (own-core physics).
fn fgain(f: Float, fc: Float, bw: Float) -> Float {
    let d: Float = f - fc
    return (bw * bw) / (d * d + bw * bw)
}

// His PITCH MELODY from measured prosody [f0_median, f0_min, f0_max, declination].
// A natural statement shape over the utterance: onset rise to the median, a
// near-flat body (his declination is ~0.6 Hz/s), and a final fall toward f0_min.
// Follows his melody + range, not a fixed 0.85 decline. gidx/total = position.
fn prosody_f0(pros: [Int], gidx: Int, total: Int) -> Int {
    let med: Int = native_list_get(pros, 0)
    let lo: Int = native_list_get(pros, 1)
    let hi: Int = native_list_get(pros, 2)
    let p: Int = gidx * 1000 / total
    let f0: Int = med
    if p < 150 {
        f0 = lo + (med - lo) * p / 150
    } else {
        if p > 700 {
            f0 = med + (lo - med) * (p - 700) / 300
        } else {
            f0 = med
        }
    }
    if f0 < lo {
        f0 = lo
    }
    if f0 > hi {
        f0 = hi
    }
    return f0
}

// -- The render: phoneme codes + voice signature -> normalized PCM samples ----
// Formant geometry per phoneme is READ FROM THE ENGRAM (pmap) via phon_geo — no
// table in code. The optional ACCENT map (amap) composes a transform onto the
// voice (voice (+) accent, separable): RP formant overrides read from the accent
// manifold + a non-rhotic coda-R drop. Empty amap = base General-American.
// Synthesis is FLOAT: a real phase accumulator + math_sin, superposition physics.
fn synth_codes_accent(codes0: [String], voice: [String], pmap: [String], amap: [String], vset: [String], vmap: [String], prosody: [Int]) -> [Int] {
    let sr: Int = 16000
    let srf: Float = 16000.0
    let two_pi: Float = 6.283185307
    let kf: Int = voice_get_int(voice, "kf")
    let f0s: Int = voice_get_int(voice, "f0")
    let f0e: Int = voice_get_int(voice, "f0_end")
    let durm: Int = voice_get_int(voice, "dur")
    if kf <= 0 {
        kf = 1000
    }
    if durm <= 0 {
        durm = 1000
    }
    let use_accent: Int = 0
    if native_list_len(amap) > 0 {
        use_accent = 1
    }
    let codes: [String] = codes0
    if use_accent == 1 {
        if is_nonrhotic(amap) == 1 {
            codes = apply_rhoticity(codes0, vset)
        }
    }
    let nc: Int = native_list_len(codes)

    // pass 1: per-segment sample counts + total
    let segn: [Int] = native_list_empty()
    let total: Int = 0
    let ci: Int = 0
    while ci < nc {
        let code: String = native_list_get(codes, ci)
        let p: [Int] = phon_geo(pmap, code)
        let durms: Int = native_list_get(p, 8)
        let ns: Int = durms * 16 * durm / 1000
        segn = native_list_append(segn, ns)
        total = total + ns
        ci = ci + 1
    }
    if total <= 0 {
        total = 1
    }

    // pass 2: synthesize
    let samples: [Int] = native_list_empty()
    let phasef: Float = 0.0
    let gidx: Int = 0
    let prevF1: Int = 500 * kf / 1000
    let prevF2: Int = 1500 * kf / 1000
    let prevF3: Int = 2500 * kf / 1000
    let nstate: Int = 22695
    let maxabs: Int = 1

    let ci2: Int = 0
    while ci2 < nc {
        let code: String = native_list_get(codes, ci2)
        let p: [Int] = phon_geo(pmap, code)
        let rf1: Int = native_list_get(p, 0)
        let rf2: Int = native_list_get(p, 1)
        let rf3: Int = native_list_get(p, 2)
        if use_accent == 1 {
            let ov: [Int] = accent_formants(amap, code)
            if native_list_len(ov) >= 3 {
                rf1 = native_list_get(ov, 0)
                rf2 = native_list_get(ov, 1)
                rf3 = native_list_get(ov, 2)
            }
        }
        // HIS measured vowel target overrides the generic/kf path (absolute Hz —
        // his formants already encode his vocal tract, so no kf scaling).
        let usekf: Int = 1
        if native_list_len(vmap) > 0 {
            let hv: [Int] = vmap_get(vmap, code)
            if native_list_len(hv) >= 3 {
                rf1 = native_list_get(hv, 0)
                rf2 = native_list_get(hv, 1)
                rf3 = native_list_get(hv, 2)
                usekf = 0
            }
        }
        let F1t: Int = rf1 * kf / 1000
        let F2t: Int = rf2 * kf / 1000
        let F3t: Int = rf3 * kf / 1000
        if usekf == 0 {
            F1t = rf1
            F2t = rf2
            F3t = rf3
        }
        let B1: Int = native_list_get(p, 3)
        let B2: Int = native_list_get(p, 4)
        let B3: Int = native_list_get(p, 5)
        let voiced: Int = native_list_get(p, 6)
        let ampv: Int = native_list_get(p, 9)
        let ns: Int = native_list_get(segn, ci2)
        let trans: Int = ns / 2
        if trans > 560 {
            trans = 560
        }
        if trans < 1 {
            trans = 1
        }
        let k: Int = 0
        while k < ns {
            let cF1: Int = F1t
            let cF2: Int = F2t
            let cF3: Int = F3t
            if k < trans {
                cF1 = prevF1 + (F1t - prevF1) * k / trans
                cF2 = prevF2 + (F2t - prevF2) * k / trans
                cF3 = prevF3 + (F3t - prevF3) * k / trans
            }
            let f0c: Int = f0s + (f0e - f0s) * gidx / total
            if native_list_len(prosody) >= 3 {
                f0c = prosody_f0(prosody, gidx, total)
            }
            if f0c < 40 {
                f0c = 40
            }
            let env: Int = 32767
            let ar: Int = 96
            if k < ar {
                env = 32767 * k / ar
            }
            let tail: Int = ns - k
            if tail < ar {
                env = 32767 * tail / ar
            }
            let f0cf: Float = int_to_float(f0c)
            phasef = phasef + two_pi * f0cf / srf
            if phasef > two_pi {
                phasef = phasef - two_pi
            }

            let s: Int = 0
            if voiced == 1 {
                let cF1f: Float = int_to_float(cF1)
                let cF2f: Float = int_to_float(cF2)
                let cF3f: Float = int_to_float(cF3)
                let B1f: Float = int_to_float(B1)
                let B2f: Float = int_to_float(B2)
                let B3f: Float = int_to_float(B3)
                let acc: Float = 0.0
                let h: Int = 1
                while h <= 50 {
                    let hf: Float = int_to_float(h)
                    let fhf: Float = hf * f0cf
                    if fhf < 7900.0 {
                        let sv: Float = math_sin(phasef * hf)
                        let src: Float = 1.0 / hf
                        let g1: Float = fgain(fhf, cF1f, B1f)
                        let g2: Float = fgain(fhf, cF2f, B2f)
                        let g3: Float = fgain(fhf, cF3f, B3f)
                        let g: Float = g1 + g2 + g3
                        acc = acc + src * g * sv
                    }
                    h = h + 1
                }
                s = float_to_int(acc * 4000.0)
            } else {
                if ampv > 0 {
                    nstate = nstate * 1103515245 + 12345
                    nstate = nstate - (nstate / 2147483648) * 2147483648
                    if nstate < 0 {
                        nstate = 0 - nstate
                    }
                    let nz: Int = nstate / 32768 - 32768
                    s = nz
                }
            }
            s = s * ampv / 100
            s = s * env / 32767
            samples = native_list_append(samples, s)
            let a: Int = s
            if a < 0 {
                a = 0 - a
            }
            if a > maxabs {
                maxabs = a
            }
            gidx = gidx + 1
            k = k + 1
        }
        prevF1 = F1t
        prevF2 = F2t
        prevF3 = F3t
        ci2 = ci2 + 1
    }

    // normalize to int16 range (~22000 peak)
    let out: [Int] = native_list_empty()
    let ntot: Int = native_list_len(samples)
    let j: Int = 0
    while j < ntot {
        let raw: Int = native_list_get(samples, j)
        let v: Int = raw * 22000 / maxabs
        out = native_list_append(out, v)
        j = j + 1
    }
    return out
}

// GA convenience wrapper (no accent) — keeps the base render path.
fn synth_codes(codes: [String], voice: [String], pmap: [String]) -> [Int] {
    let noacc: [String] = native_list_empty()
    let novset: [String] = native_list_empty()
    let novmap: [String] = native_list_empty()
    let nopros: [Int] = native_list_empty()
    return synth_codes_accent(codes, voice, pmap, noacc, novset, novmap, nopros)
}

// -- Voice-by-imitation: HEAR a PCM sample -> extract the voice signature -----
// Pitch by autocorrelation; vocal-tract scale (kf) from the F1 formant peak of a
// heard sustained vowel /AA/ (nominal F1 = 730 Hz) via an integer DFT. The
// analyzer sees ONLY the PCM samples — never the source signature numbers — so
// recovery is genuinely by ear.
fn voice_f0(samples: [Int], sr: Int) -> Int {
    let n: Int = native_list_len(samples)
    let start: Int = n / 4
    let end: Int = n * 3 / 4
    // bound the analysis window so accumulators can never overflow on long input
    if end - start > 6000 {
        end = start + 6000
    }
    let minlag: Int = sr / 300
    let maxlag: Int = sr / 75
    let best: Int = 0
    let bestlag: Int = minlag
    let lag: Int = minlag
    while lag <= maxlag {
        let sum: Int = 0
        let i: Int = start
        while i < end {
            let ai: Int = native_list_get(samples, i)
            let bi: Int = native_list_get(samples, i + lag)
            sum = sum + ai * bi / 256
            i = i + 2
        }
        if sum > best {
            best = sum
            bestlag = lag
        }
        lag = lag + 1
    }
    if bestlag < 1 {
        bestlag = 1
    }
    return sr / bestlag
}

fn voice_peak_in_band(samples: [Int], sr: Int, flo: Int, fhi: Int) -> Int {
    let n: Int = native_list_len(samples)
    let start: Int = n / 4
    let end: Int = n * 3 / 4
    // bound the DFT window: re/im are accumulated /4096, and re*re must stay in
    // int64 — cap terms so (window/2)*(peak_term) squared cannot overflow.
    if end - start > 3000 {
        end = start + 3000
    }
    let bestmag: Int = 0
    let bestf: Int = flo
    let f: Int = flo
    while f <= fhi {
        let re: Int = 0
        let im: Int = 0
        let i: Int = start
        while i < end {
            let x: Int = native_list_get(samples, i)
            let ph: Int = i * f * 65536 / sr
            ph = ph - (ph / 65536) * 65536
            let cq: Int = sp_cos(ph)
            let sq: Int = sp_sin(ph)
            re = re + x * cq / 4096
            im = im + x * sq / 4096
            i = i + 2
        }
        let mag: Int = re * re + im * im
        if mag > bestmag {
            bestmag = mag
            bestf = f
        }
        f = f + 25
    }
    return bestf
}

// Analyze a heard sustained /AA/ -> a full voice signature (by ear).
fn voice_analyze(samples: [Int], sr: Int) -> [String] {
    let f0: Int = voice_f0(samples, sr)
    let f1: Int = voice_peak_in_band(samples, sr, 450, 1150)
    let kf: Int = 1000 * f1 / 730
    let f0e: Int = f0 * 85 / 100
    return voice_new("imitated", f0, f0e, kf, 1000, 1000, 8)
}