Environmental Sound Classification

Classify environmental sounds into categories following UrbanSound8K and ESC-50 datasets.

🎧

audio annotation

Configuration Fileconfig.yaml

task_name: "Environmental Sound Classification"

# Server configuration
server:
  port: 8000

# Audio settings
audio:
  enabled: true
  display: waveform
  waveform_color: "#10B981"
  progress_color: "#34D399"
  speed_control: true

# Data configuration
data_files:
  - path: data/environmental_sounds.json
    audio_field: audio_file

# Annotation schemes
annotation_schemes:
  # Primary sound category (UrbanSound8K classes)
  - annotation_type: radio
    name: sound_category
    description: "Select the primary sound category"
    labels:
      - Air conditioner
      - Car horn
      - Children playing
      - Dog bark
      - Drilling
      - Engine idling
      - Gun shot
      - Jackhammer
      - Siren
      - Street music
    keyboard_shortcuts:
      "Air conditioner": "1"
      "Car horn": "2"
      "Children playing": "3"
      "Dog bark": "4"
      "Drilling": "5"
      "Engine idling": "6"
      "Gun shot": "7"
      "Jackhammer": "8"
      "Siren": "9"
      "Street music": "0"

  # Sound prominence
  - annotation_type: radio
    name: prominence
    description: "How prominent is the target sound?"
    labels:
      - Dominant (clearly the main sound)
      - Present (audible but not dominant)
      - Background (barely audible)
      - Absent (wrong label)

  # Audio quality
  - annotation_type: radio
    name: audio_quality
    description: "Rate the recording quality"
    labels:
      - Clear (easy to identify)
      - Moderate (some noise)
      - Poor (difficult to identify)
      - Unusable (cannot determine)

  # Confidence
  - annotation_type: likert
    name: confidence
    description: "How confident are you in your classification?"
    size: 5
    min_label: "Guessing"
    max_label: "Certain"

# User settings
allow_all_users: true
instances_per_annotator: 300

# Output
output:
  path: annotations/
  format: json

Get This Design

This design is available in our showcase. Copy the configuration below to get started.

Quick start:

# Create your project folder
mkdir environmental-sound-classification
cd environmental-sound-classification
# Copy config.yaml from above
potato start config.yaml

Details

Annotation Types

radio

Domain

Audio

Use Cases

sound classificationenvironmental audiourban sound analysis

Related Designs

Acoustic Scene Classification

Classify audio recordings by acoustic environment following the TUT/DCASE dataset format.

radiolikert

Audio-Visual Sentiment Analysis

Rate sentiment in speech segments following CMU-MOSI and CMU-MOSEI multimodal annotation protocols.

likertradio

Keyword Spotting

Classify spoken commands and keywords following the Google Speech Commands dataset format.