voice-cat/core/src/audio/apm_processor.cpp

#include "audio/apm_processor.h"

#include <algorithm>
#include <atomic>
#include <chrono>
#include <cmath>

#ifdef VOICECAT_HAS_NS
#include "rnnoise.h"
#endif

namespace voicecat::audio {

namespace {
int64_t steady_now_ms() {
    return std::chrono::duration_cast<std::chrono::milliseconds>(
               std::chrono::steady_clock::now().time_since_epoch())
        .count();
}
}  // namespace

// ── ApmPassthrough ────────────────────────────────────────────────────────────
// No-op: returns true (VAD always open), does not modify PCM.
// Replaced by WebrtcApmProcessor when VOICECAT_HAS_APM is defined.
class ApmPassthrough final : public ApmProcessor {
   public:
    void process_render(const int16_t*, int, int) override {}
    bool process_capture(int16_t*, int, int) override { return true; }
};

// ── EnergyVadProcessor ──────────────────────────────────────────────────────
// Lightweight, dependency-free energy/RMS VAD — see apm_processor.h's create_vad() doc comment
// for why this exists instead of a real APM. No AEC (process_render is a no-op); doesn't modify
// the PCM it's given, only inspects it.
class EnergyVadProcessor final : public ApmProcessor {
   public:
    EnergyVadProcessor(float rms_threshold, int64_t hang_time_ms)
        : threshold_(rms_threshold), hang_time_ms_(hang_time_ms) {}

    void process_render(const int16_t*, int, int) override {}

    bool process_capture(int16_t* pcm, int samples, int /*sample_rate*/) override {
        if (samples > 0) {
            double sum_sq = 0.0;
            for (int i = 0; i < samples; ++i) {
                double s = static_cast<double>(pcm[i]) / 32768.0;
                sum_sq += s * s;
            }
            double rms = std::sqrt(sum_sq / samples);
            if (rms >= threshold_.load(std::memory_order_relaxed)) last_voice_ms_ = steady_now_ms();
        }
        return (steady_now_ms() - last_voice_ms_) < hang_time_ms_;
    }

    void set_threshold(float t) override {
        threshold_.store(t, std::memory_order_relaxed);
    }

   private:
    std::atomic<float> threshold_;
    int64_t            hang_time_ms_;
    int64_t last_voice_ms_ = 0;  // epoch start -> gate begins closed until first loud frame
};

#ifdef VOICECAT_HAS_NS
// ── RnnoiseProcessor ─────────────────────────────────────────────────────────
// Real noise suppression via vendored RNNoise (third_party/rnnoise; docs/voice.md §10-11).
// RNNoise is a mono, 48 kHz, fixed 480-sample (10 ms) speech denoiser; our engine clock is fixed
// at 48 kHz and every Opus frame size (480/960/1920/2880) is a multiple of 480, so we process
// whole 480-sample chunks with no resampling and no cross-call carry. Mono only — callers gate
// on a single channel (a stereo screen-audio share is never voice and isn't denoised).
//
// RT-safety (docs/architecture.md §3): the DenoiseState and the float scratch are allocated in the
// ctor; process_capture() does no allocation/locking. The state is owned per-stream (recv) or
// per-mic (send) so it persists across calls, which is exactly what RNNoise's overlap needs.
class RnnoiseProcessor final : public ApmProcessor {
   public:
    RnnoiseProcessor() : st_(rnnoise_create(nullptr)) {}
    ~RnnoiseProcessor() override {
        if (st_) rnnoise_destroy(st_);
    }

    void process_render(const int16_t*, int, int) override {}  // NS needs no AEC reference

    bool process_capture(int16_t* pcm, int samples, int sample_rate) override {
        // RNNoise is 48 kHz only; anything else passes through untouched (our clock is 48 kHz, so
        // this guard never trips in practice — it's just a correctness backstop).
        if (!st_ || sample_rate != 48000) return true;
        for (int off = 0; off + kFrame <= samples; off += kFrame) {
            for (int i = 0; i < kFrame; ++i) in_[i] = static_cast<float>(pcm[off + i]);
            rnnoise_process_frame(st_, out_, in_);
            for (int i = 0; i < kFrame; ++i) {
                int32_t v = static_cast<int32_t>(std::lround(out_[i]));
                pcm[off + i] = static_cast<int16_t>(std::clamp(v, -32768, 32767));
            }
        }
        return true;  // NS doesn't gate; the send path's VAD stays a separate stage
    }

   private:
    static constexpr int kFrame = 480;  // rnnoise_get_frame_size()
    DenoiseState* st_;
    float in_[kFrame];
    float out_[kFrame];
};
#endif  // VOICECAT_HAS_NS

std::unique_ptr<ApmProcessor> ApmProcessor::create() {
#ifdef VOICECAT_HAS_NS
    return std::make_unique<RnnoiseProcessor>();
#else
    return std::make_unique<ApmPassthrough>();
#endif
}

std::unique_ptr<ApmProcessor> ApmProcessor::create_vad(float rms_threshold,
                                                        int64_t hang_time_ms) {
    return std::make_unique<EnergyVadProcessor>(rms_threshold, hang_time_ms);
}

}  // namespace voicecat::audio