Détection et étiquetage d'événements audio

La détection d'événements audio identifie des sons spécifiques dans les enregistrements - de la parole et de la musique aux sons environnementaux et événements acoustiques. Ce tutoriel couvre l'annotation basée sur les horodatages pour entraîner des modèles de reconnaissance sonore.

Types d'annotation d'événements audio

Étiquetage au niveau du clip : Étiqueter des clips audio entiers
Détection temporelle : Marquer les temps de début/fin des événements
Étiquetage fort : Horodatages précis pour chaque événement
Étiquetage faible : Présence/absence sans horodatage

Étiquetage sonore au niveau du clip

Pour les clips courts avec des événements uniques :

yaml

annotation_task_name: "Sound Event Classification"
 
data_files:
  - data/audio_clips.json
 
item_properties:
  audio_path: audio_path
 
annotation_schemes:
  - annotation_type: audio_annotation
    audio_display: waveform
    waveform_color: "#10B981"
    progress_color: "#34D399"
    name: sound_class
    description: "What sound is in this clip?"
    labels:
      - Dog bark
      - Car horn
      - Siren
      - Music
      - Speech
      - Footsteps
      - Door knock
      - Glass breaking
      - Gunshot
      - Baby cry
      - Other
      - Silence/noise only

Détection temporelle d'événements sonores

Marquer quand les événements se produisent :

yaml

annotation_task_name: "Sound Event Detection"
 
data_files:
  - data/recordings.json
 
item_properties:
  audio_path: audio_path
 
annotation_schemes:
  - annotation_type: audio_annotation
    audio_display: waveform
    height: 150
    waveform_color: "#6366F1"
    progress_color: "#A5B4FC"
    show_timestamps: true
    enable_regions: true
    speed_control: true
    name: events
    description: "Mark all sound events with timestamps"
    labels:
      - name: speech
        color: "#3B82F6"
      - name: music
        color: "#8B5CF6"
      - name: vehicle
        color: "#EF4444"
      - name: animal
        color: "#F59E0B"
      - name: nature
        color: "#10B981"
      - name: mechanical
        color: "#6B7280"
    allow_overlap: true
    min_duration: 0.1

Configuration complète d'événements audio

yaml

annotation_task_name: "AudioSet-Style Event Detection"
 
data_files:
  - data/audio_10sec.json
 
item_properties:
  audio_path: audio_url
 
annotation_schemes:
  # Temporal event marking with audio playback
  - annotation_type: audio_annotation
    audio_display: waveform
    waveform_color: "#059669"
    progress_color: "#34D399"
    cursor_color: "#F59E0B"
    height: 128
    show_timestamps: true
    time_format: "ss.ms"
    show_duration: true
    speed_control: true
    speed_options: [0.5, 0.75, 1.0, 1.5]
    enable_regions: true
    region_snap: 0.05
    name: sound_events
    description: "Mark all distinct sound events"
    labels:
      # Human sounds
      - name: Speech
        color: "#3B82F6"
        keyboard_shortcut: "1"
        category: human
      - name: Singing
        color: "#8B5CF6"
        keyboard_shortcut: "2"
        category: human
      - name: Laughter
        color: "#EC4899"
        category: human
      - name: Cough/Sneeze
        color: "#F472B6"
        category: human
 
      # Music
      - name: Music
        color: "#A855F7"
        keyboard_shortcut: "m"
        category: music
      - name: Musical instrument
        color: "#7C3AED"
        category: music
 
      # Animals
      - name: Dog
        color: "#F59E0B"
        keyboard_shortcut: "d"
        category: animal
      - name: Cat
        color: "#FBBF24"
        category: animal
      - name: Bird
        color: "#FCD34D"
        category: animal
 
      # Vehicles
      - name: Car
        color: "#EF4444"
        keyboard_shortcut: "c"
        category: vehicle
      - name: Motorcycle
        color: "#DC2626"
        category: vehicle
      - name: Siren
        color: "#B91C1C"
        category: vehicle
      - name: Aircraft
        color: "#991B1B"
        category: vehicle
 
      # Environment
      - name: Rain
        color: "#06B6D4"
        category: nature
      - name: Thunder
        color: "#0891B2"
        category: nature
      - name: Wind
        color: "#0E7490"
        category: nature
      - name: Water
        color: "#0D9488"
        category: nature
 
      # Domestic
      - name: Door
        color: "#84CC16"
        category: domestic
      - name: Alarm
        color: "#65A30D"
        category: domestic
      - name: Appliance
        color: "#4D7C0F"
        category: domestic
 
      # Other
      - name: Noise/Unknown
        color: "#6B7280"
        keyboard_shortcut: "n"
        category: other
 
    allow_overlap: true
    min_duration: 0.1
    show_labels_on_waveform: true
 
    # Segment attributes
    segment_attributes:
      - name: confidence
        type: radio
        options: [Clear, Moderate, Faint]
      - name: foreground
        type: checkbox
        description: "Is this the main/foreground sound?"
 
  # Clip-level tags (weak labels)
  - annotation_type: multiselect
    name: clip_tags
    description: "What sounds are present anywhere in this clip?"
    labels:
      - Speech
      - Music
      - Vehicle sounds
      - Animal sounds
      - Nature sounds
      - Domestic sounds
      - Silence
    min_selections: 1
 
  # Audio quality
  - annotation_type: radio
    name: quality
    description: "Recording quality"
    labels:
      - Clean (clear sounds)
      - Moderate noise
      - Very noisy
      - Distorted/clipped
 
annotation_guidelines:
  title: "Sound Event Detection Guide"
  content: |
    ## Your Task
    Mark the START and END times of each distinct sound event.
 
    ## Event Detection Rules
    - Mark sounds that are clearly audible
    - Include overlapping sounds (use multiple labels)
    - Short sounds (<100ms) may be a single point
 
    ## Segment Boundaries
    - Start: When sound becomes audible
    - End: When sound fades or stops
 
    ## Confidence Levels
    - Clear: Easily identifiable
    - Moderate: Reasonably sure
    - Faint: Background, hard to identify
 
    ## Foreground vs Background
    - Foreground: Main focus of audio
    - Background: Ambient sounds

Format de sortie

json

{
  "id": "clip_001",
  "audio_url": "/audio/street_scene.wav",
  "duration": 10.0,
  "annotations": {
    "sound_events": [
      {
        "label": "Speech",
        "start": 0.5,
        "end": 3.2,
        "attributes": {
          "confidence": "Clear",
          "foreground": true
        }
      },
      {
        "label": "Car",
        "start": 1.8,
        "end": 4.5,
        "attributes": {
          "confidence": "Moderate",
          "foreground": false
        }
      },
      {
        "label": "Dog",
        "start": 6.1,
        "end": 6.8,
        "attributes": {
          "confidence": "Clear",
          "foreground": true
        }
      }
    ],
    "clip_tags": ["Speech", "Vehicle sounds", "Animal sounds"],
    "quality": "Moderate noise"
  }
}

Pré-annotation avec un détecteur

Utilisez les prédictions d'un modèle comme point de départ :

yaml

pre_annotation:
  enabled: true
  field: detected_events
  show_confidence: true
  confidence_threshold: 0.3
  allow_modification: true

Conseils pour l'annotation d'événements audio

Bons écouteurs : Essentiels pour détecter les sons subtils
Environnement calme : Le bruit ambiant affecte la perception
Passes multiples : Premier passage pour identifier, second pour affiner les horodatages
Lecture lente : Utilisez 0.5x pour des limites précises
Critères cohérents : Définissez clairement le seuil d'"audible"

Prochaines étapes

Ajoutez la classification musicale pour le contenu musical
Découvrez la diarisation des locuteurs pour la parole
Mettez en place un contrôle qualité pour la détection d'événements

Documentation audio complète sur /docs/features/audio-annotation.