id: https://nde.nl/ontology/hc/class/AudioEventSegment
name: audio_event_segment_class
title: Audio Event Segment Class
description: 'A temporal segment of audio containing a detected audio event (speech, music, silence, etc.).


  MIGRATED from audio_event_segments slot (Rule 53).

  Uses generic has_or_had_segment slot with range narrowed to AudioEventSegment.

  '
imports:
- linkml:types
- ../slots/start_seconds
- ../slots/has_or_had_time_interval
- ./TimeInterval
- ../slots/start_time
- ../slots/segment_index
- ../slots/segment_text
- ../slots/is_or_was_generated_by
- ./GenerationEvent
- ./ConfidenceScore
- ../slots/specificity_annotation
- ../slots/has_or_had_score
- ./SpecificityAnnotation
- ./TemplateSpecificityScore
- ./TemplateSpecificityType
- ./TemplateSpecificityTypes
- ../enums/AudioEventTypeEnum
- ../slots/has_or_had_type
prefixes:
  linkml: https://w3id.org/linkml/
  hc: https://nde.nl/ontology/hc/
  schema: http://schema.org/
  dcterms: http://purl.org/dc/terms/
  crm: http://www.cidoc-crm.org/cidoc-crm/
  oa: http://www.w3.org/ns/oa#
  ma: http://www.w3.org/ns/ma-ont#
default_prefix: hc
classes:
  AudioEventSegment:
    class_uri: hc:AudioEventSegment
    description: 'A temporal segment of audio containing a detected audio event.


      **DEFINITION**:


      AudioEventSegment represents a bounded temporal portion of audio content

      where a specific type of audio event has been detected. This includes:

      - Speech segments (with optional speaker/language info)

      - Music segments (with optional genre/type info)

      - Silence segments (gaps between audio)

      - Sound event segments (applause, laughter, ambient sounds)

      - Noise segments (for quality assessment)


      **RELATIONSHIP TO VideoTimeSegment**:


      AudioEventSegment is a specialized sibling of VideoTimeSegment:

      - Both extend CIDOC-CRM E52_Time-Span concept

      - VideoTimeSegment: general video temporal segments

      - AudioEventSegment: audio-specific event segments


      **AUDIO EVENT TYPES**:


      | Event Type | Description | Example |

      |------------|-------------|---------|

      | SPEECH | Human speech detected | Interview segment |

      | MUSIC | Music detected | Background soundtrack |

      | SILENCE | Very low or no audio | Gap between segments |

      | SOUND_EVENT | Non-speech/music sounds | Applause, footsteps |

      | NOISE | Noise/interference | Quality issue marker |

      | MIXED | Multiple event types | Overlapping audio |


      **HERITAGE USE CASES**:


      | Content Type | Application |

      |--------------|-------------|

      | Oral histories | Speech segment identification |

      | Virtual tours | Background music detection |

      | Lecture recordings | Audience reaction segments |

      | Conservation videos | Narration vs ambient sound |

      | Archival footage | Audio quality assessment |


      **PROVENANCE**:


      Created as part of slot migration (Rule 53) from deprecated

      `audio_event_segments` slot to generic `has_or_had_segment` pattern.

      '
    exact_mappings:
    - hc:AudioEventSegment
    close_mappings:
    - crm:E52_Time-Span
    - ma:MediaFragment
    related_mappings:
    - oa:FragmentSelector
    slots:
    - has_or_had_time_interval
    - segment_index
    - segment_text
    - is_or_was_generated_by
    - has_or_had_type
    - specificity_annotation
    - has_or_had_score
    attributes:
      start_seconds:
        range: float
        required: true
        minimum_value: 0.0
        description: Start time in seconds for this audio event segment. Defined as attribute.
        examples:
        - value: 0.0
          description: Audio event starts at beginning
        - value: 45.5
          description: Audio event starts at 45.5 seconds
      start_time:
        range: string
        required: false
        pattern: ^PT(\d+H)?(\d+M)?(\d+(\.\d+)?S)?$
        description: Start time in ISO 8601 duration format. Defined as attribute.
        examples:
        - value: PT0M30S
          description: 30 seconds from start
    slot_usage:
      has_or_had_type:
        range: AudioEventTypeEnum
        required: true
        description: The type of audio event detected in this segment.
        examples:
        - value: SPEECH
          description: Speech detected in this segment
        - value: MUSIC
          description: Music detected in this segment
      has_or_had_time_interval:
        range: TimeInterval
        required: true
        inlined: true
        description: Duration of audio segment. Replaces end_seconds/end_time. Use duration_value for ISO 8601 (e.g. PT15S).
        examples:
        - value:
            duration_value: PT0M15S
          description: 15 second duration
      segment_text:
        range: string
        required: false
        description: Text content for this segment (e.g., speech transcript, music description).
        examples:
        - value: Welcome to the Rijksmuseum
          description: Speech transcript text
        - value: Classical background music
          description: Music segment description
      is_or_was_generated_by:
        range: GenerationEvent
        required: false
        inlined: true
        description: 'Generation event containing confidence score for audio event detection. MIGRATED 2026-01-19: Replaces confidence slot with structured pattern.'
        examples:
        - value:
            has_or_had_score:
              has_or_had_score: 0.95
              has_or_had_method: audio_classification
          description: High confidence audio event detection
    comments:
    - Audio event segment for speech, music, silence, sound event detection
    - Temporal boundaries with start/end seconds (primary) and ISO 8601 (secondary)
    - Confidence scoring for AI-generated detections
    - Part of Rule 53 slot migration from audio_event_segments
    see_also:
    - https://www.w3.org/TR/media-frags/
    - https://www.w3.org/ns/ma-ont
    annotations:
      specificity_score: 0.1
      specificity_rationale: Generic utility class/slot created during migration
      custodian_types: "['*']"
      custodian_types_rationale: Universal utility concept