# Multimodal noise configuration for robustness experiments (P0-4)
# Each variant defines noise applied per modality.
# Run: python scripts/preprocess/generate_noise.py \
#        --config configs/noise_configs.yaml \
#        --data_dir $ZSY/multimodal_affect/data/iemocap

variants:

  # ── Variant 1: Light Gaussian across all modalities ───────────────────
  - name: gaussian_light
    description: "Mild Gaussian noise on all modalities (σ=0.05)"
    noise:
      text:
        type: gaussian
        intensity: 0.05
      audio:
        type: gaussian
        intensity: 0.05
      visual:
        type: gaussian
        intensity: 0.05

  # ── Variant 2: Heavy Gaussian ─────────────────────────────────────────
  - name: gaussian_heavy
    description: "Strong Gaussian noise on all modalities (σ=0.20)"
    noise:
      text:
        type: gaussian
        intensity: 0.20
      audio:
        type: gaussian
        intensity: 0.20
      visual:
        type: gaussian
        intensity: 0.20

  # ── Variant 3: Missing modality – audio dropped ───────────────────────
  - name: missing_audio
    description: "Audio features zeroed out (100% drop)"
    noise:
      text:
        type: gaussian
        intensity: 0.0
      audio:
        type: masking
        intensity: 1.0        # mask ALL dims
      visual:
        type: gaussian
        intensity: 0.0

  # ── Variant 4: Missing modality – visual dropped ──────────────────────
  - name: missing_visual
    description: "Visual features zeroed out"
    noise:
      text:
        type: gaussian
        intensity: 0.0
      audio:
        type: gaussian
        intensity: 0.0
      visual:
        type: missing_modality
        intensity: 1.0

  # ── Variant 5: Text word-drop ─────────────────────────────────────────
  - name: text_word_drop_30
    description: "30% token dropout in text modality"
    noise:
      text:
        type: word_drop
        intensity: 0.30
      audio:
        type: gaussian
        intensity: 0.0
      visual:
        type: gaussian
        intensity: 0.0

  # ── Variant 6: Audio feature masking ─────────────────────────────────
  - name: audio_masking_50
    description: "50% of audio feature dimensions masked"
    noise:
      text:
        type: gaussian
        intensity: 0.0
      audio:
        type: masking
        intensity: 0.50
      visual:
        type: gaussian
        intensity: 0.0

  # ── Variant 7: Realistic mixed noise ─────────────────────────────────
  - name: realistic_mixed
    description: >
      Realistic scenario: moderate text corruption, noisy audio,
      partial visual occlusion
    noise:
      text:
        type: word_drop
        intensity: 0.15
      audio:
        type: gaussian
        intensity: 0.10
      visual:
        type: occlusion
        intensity: 0.25

  # ── Variant 8: Asynchronous noise (time-shifted audio) ───────────────
  - name: audio_time_mask
    description: "Audio time-step masking (30%) simulates dropped frames"
    noise:
      text:
        type: gaussian
        intensity: 0.0
      audio:
        type: time_mask
        intensity: 0.30
      visual:
        type: gaussian
        intensity: 0.0