90842851c2
- Created 'updated_at.yaml' to record the last modified date and time of entities, including multilingual descriptions and structured aliases. - Created 'written_in.yaml' to specify the language in which content is composed, covering both natural and programming languages, with detailed comments and close ontology mappings.
173 lines
4.6 KiB
YAML
173 lines
4.6 KiB
YAML
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_segment slot with range narrowed to AudioEventSegment.
|
|
|
|
'
|
|
imports:
|
|
- linkml:types
|
|
- ../enums/AudioEventTypeEnum
|
|
- ../slots/20260202_matang/has_score
|
|
- ../slots/20260202_matang/has_time_interval
|
|
- ../slots/20260202_matang/has_type
|
|
- ../slots/20260202_matang/generated_by
|
|
- ../slots/20260202_matang/new/segment_index
|
|
- ../slots/20260202_matang/new/segment_text
|
|
- ../slots/20260202_matang/new/start_seconds
|
|
- ../slots/20260202_matang/new/start_time
|
|
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_segment` pattern.
|
|
|
|
'
|
|
exact_mappings:
|
|
- hc:AudioEventSegment
|
|
close_mappings:
|
|
- crm:E52_Time-Span
|
|
- ma:MediaFragment
|
|
related_mappings:
|
|
- oa:FragmentSelector
|
|
slots:
|
|
- has_time_interval
|
|
- segment_index
|
|
- segment_text
|
|
- generated_by
|
|
- has_type
|
|
- has_score
|
|
- start_seconds
|
|
- start_time
|
|
slot_usage:
|
|
has_type:
|
|
range: AudioEventTypeEnum
|
|
required: true
|
|
examples:
|
|
- value: SPEECH
|
|
- value: MUSIC
|
|
has_time_interval:
|
|
range: TimeInterval
|
|
required: true
|
|
inlined: true
|
|
examples:
|
|
- value: null
|
|
segment_text:
|
|
# range: string
|
|
required: false
|
|
examples:
|
|
- value: Welcome to the Rijksmuseum
|
|
- value: Classical background music
|
|
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_score:
|
|
has_score: 0.95
|
|
has_method: audio_classification
|
|
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: '[''*'']'
|