Skip to content
beginneraudio

Music Genre Classification

Classify music clips into genres and subgenres with mood and instrumentation tags.

Get This Design

View on GitHub(opens in a new tab)

Clone or download from the repository

Quick start:

bash
git clone https://github.com/davidjurgens/potato-showcase.git
cd potato-showcase/audio/music-genre-classification
potato start config.yaml

Configuration File

yaml
# Music Genre Classification Configuration
# Classify music clips into genres with mood and instrumentation tags

task_dir: "."
annotation_task_name: "Music Genre Classification"

data_files:
  - "data/music_clips.json"

item_properties:
  id_key: "id"
  text_key: "title"
  audio_key: "audio_url"
  text_display_key: "title"

user_config:
  allow_all_users: true

annotation_schemes:
  - annotation_type: "radio"
    name: "primary_genre"
    description: "What is the primary genre of this music?"
    labels:
      - name: "Rock"
        key_value: "1"
      - name: "Pop"
        key_value: "2"
      - name: "Hip-Hop/Rap"
        key_value: "3"
      - name: "Electronic/Dance"
        key_value: "4"
      - name: "Jazz"
        key_value: "5"
      - name: "Classical"
        key_value: "6"
      - name: "R&B/Soul"
        key_value: "7"
      - name: "Country"
        key_value: "8"
      - name: "Folk/Acoustic"
        key_value: "9"
      - name: "Metal"
        key_value: "0"

  - annotation_type: "multiselect"
    name: "subgenres"
    description: "Select any applicable subgenres"
    labels:
      - name: "Indie"
      - name: "Alternative"
      - name: "Punk"
      - name: "Blues"
      - name: "Reggae"
      - name: "Latin"
      - name: "World Music"
      - name: "Ambient"
      - name: "Lo-fi"
      - name: "Synthwave"

  - annotation_type: "multiselect"
    name: "mood"
    description: "What mood does this music convey?"
    labels:
      - name: "Happy/Upbeat"
      - name: "Sad/Melancholic"
      - name: "Energetic"
      - name: "Calm/Relaxing"
      - name: "Aggressive"
      - name: "Romantic"
      - name: "Dark/Mysterious"
      - name: "Nostalgic"

  - annotation_type: "multiselect"
    name: "instruments"
    description: "What instruments are prominent?"
    labels:
      - name: "Vocals"
      - name: "Electric Guitar"
      - name: "Acoustic Guitar"
      - name: "Piano/Keys"
      - name: "Drums"
      - name: "Bass"
      - name: "Synthesizer"
      - name: "Strings"
      - name: "Brass"
      - name: "Woodwinds"

  - annotation_type: "radio"
    name: "tempo"
    description: "Approximate tempo"
    labels:
      - name: "Slow (< 80 BPM)"
      - name: "Medium (80-120 BPM)"
      - name: "Fast (> 120 BPM)"

audio_display:
  show_waveform: true
  playback_controls: true
  allow_speed_control: false

output: "annotation_output/"

output_annotation_dir: "annotation_output/"
output_annotation_format: "json"

Sample Data

json
[
  {
    "id": "music_001",
    "audio_url": "https://example.com/audio/clip1.mp3",
    "title": "Track A - 30 second preview",
    "duration": 30
  },
  {
    "id": "music_002",
    "audio_url": "https://example.com/audio/clip2.mp3",
    "title": "Track B - 30 second preview",
    "duration": 30
  }
]

// ... and 1 more items

Details

Annotation Types

radiomultiselect

Domain

musicentertainment

Use Cases

genre-classificationmusic-tagging

Tags

audiomusicgenreclassificationtagging

Found an issue or want to improve this design?

Open an Issue(opens in a new tab)

Related Designs

Audio Transcription Review

Review and correct automatic speech recognition transcriptions with waveform visualization.

likertmultiselect

AudioHate - Audio Hate Speech Detection

Audio hate speech detection with explanations. Annotators classify audio clips for hate speech presence, identify target groups, and note acoustic indicators such as tone, emphasis, and prosody (An et al., SIGDIAL 2024).

radiomultiselect

HatEval - Multilingual Detection of Hate Speech Against Immigrants and Women

Detection and classification of hate speech targeting immigrants and women on Twitter, including fine-grained annotation of target range (individual vs. generic) and aggressiveness. Based on SemEval-2019 Task 5 (HatEval).

radiomultiselect