1152 lines
37 KiB
YAML
1152 lines
37 KiB
YAML
# =============================================================================
|
|
# GLAM-NER: TEI P5 SPOKEN MODULE
|
|
# =============================================================================
|
|
# Module: modules/advanced/tei/spoken.yaml
|
|
# Parent: entity_annotation_rules_v1.7.0_unified.yaml
|
|
# Purpose: LinkML schema for TEI P5 Chapter 8 - Transcriptions of Speech
|
|
# Source: TEI P5 4.10.2 (September 2025) - spoken module
|
|
# =============================================================================
|
|
# This module provides LinkML class definitions for transcribing spoken
|
|
# language including utterances, pauses, vocal sounds, kinesic events,
|
|
# and paralinguistic features. Essential for oral history, sociolinguistics,
|
|
# discourse analysis, and heritage institution audio/video collections.
|
|
# =============================================================================
|
|
|
|
id: https://w3id.org/glam/ner/tei/spoken
|
|
name: glam-ner-tei-spoken
|
|
title: TEI P5 Transcriptions of Speech Module for GLAM-NER
|
|
version: "1.0.0"
|
|
license: https://creativecommons.org/licenses/by/4.0/
|
|
|
|
prefixes:
|
|
tei: http://www.tei-c.org/ns/1.0/
|
|
glam: https://w3id.org/glam/ner/
|
|
linkml: https://w3id.org/linkml/
|
|
crm: http://www.cidoc-crm.org/cidoc-crm/
|
|
schema: http://schema.org/
|
|
dcterms: http://purl.org/dc/terms/
|
|
foaf: http://xmlns.com/foaf/0.1/
|
|
prov: http://www.w3.org/ns/prov#
|
|
xsd: http://www.w3.org/2001/XMLSchema#
|
|
|
|
default_prefix: glam
|
|
default_range: string
|
|
|
|
# =============================================================================
|
|
# IMPORTS
|
|
# =============================================================================
|
|
imports:
|
|
- linkml:types
|
|
|
|
# =============================================================================
|
|
# ENUMS
|
|
# =============================================================================
|
|
enums:
|
|
|
|
# ---------------------------------------------------------------------------
|
|
# Transition Type
|
|
# ---------------------------------------------------------------------------
|
|
TransitionType:
|
|
description: |
|
|
How an utterance follows the preceding one.
|
|
Used on @trans attribute of <u> element.
|
|
permissible_values:
|
|
smooth:
|
|
description: Transition from previous speaker was smooth
|
|
pause:
|
|
description: Preceded by pause
|
|
latching:
|
|
description: Latching (no pause, no overlap)
|
|
overlap:
|
|
description: Overlapping with preceding utterance
|
|
|
|
# ---------------------------------------------------------------------------
|
|
# Paralinguistic Feature Type
|
|
# ---------------------------------------------------------------------------
|
|
ParalinguisticFeatureType:
|
|
description: |
|
|
Types of paralinguistic features that can shift during speech.
|
|
Used on @feature attribute of <shift> element.
|
|
permissible_values:
|
|
tempo:
|
|
description: Speaking tempo (fast, slow, normal)
|
|
loud:
|
|
description: Loudness (f=forte, p=piano, ff=fortissimo, pp=pianissimo)
|
|
pitch:
|
|
description: Pitch level (high, low, normal)
|
|
tension:
|
|
description: Vocal tension (tense, lax)
|
|
rhythm:
|
|
description: Speech rhythm (regular, irregular)
|
|
voice:
|
|
description: Voice quality (breathy, creaky, falsetto, whisper)
|
|
|
|
# ---------------------------------------------------------------------------
|
|
# Loudness Level
|
|
# ---------------------------------------------------------------------------
|
|
LoudnessLevel:
|
|
description: |
|
|
Musical notation for loudness levels.
|
|
Commonly used values for @new when @feature="loud".
|
|
permissible_values:
|
|
ppp:
|
|
description: Pianississimo (very very soft)
|
|
pp:
|
|
description: Pianissimo (very soft)
|
|
p:
|
|
description: Piano (soft)
|
|
mp:
|
|
description: Mezzo-piano (moderately soft)
|
|
normal:
|
|
description: Normal speaking level
|
|
mf:
|
|
description: Mezzo-forte (moderately loud)
|
|
f:
|
|
description: Forte (loud)
|
|
ff:
|
|
description: Fortissimo (very loud)
|
|
fff:
|
|
description: Fortississimo (very very loud)
|
|
|
|
# ---------------------------------------------------------------------------
|
|
# Vocal Sound Type
|
|
# ---------------------------------------------------------------------------
|
|
VocalSoundType:
|
|
description: |
|
|
Types of vocalized but not necessarily lexical sounds.
|
|
Used on @type attribute of <vocal> element.
|
|
permissible_values:
|
|
laughter:
|
|
description: Laughter
|
|
cough:
|
|
description: Coughing
|
|
sneeze:
|
|
description: Sneezing
|
|
sigh:
|
|
description: Sighing
|
|
yawn:
|
|
description: Yawning
|
|
gasp:
|
|
description: Gasping
|
|
breath:
|
|
description: Audible breathing
|
|
groan:
|
|
description: Groaning
|
|
click:
|
|
description: Clicking sound
|
|
whistle:
|
|
description: Whistling
|
|
hum:
|
|
description: Humming
|
|
sob:
|
|
description: Sobbing
|
|
throat_clear:
|
|
description: Clearing throat
|
|
filled_pause:
|
|
description: Filled pause (um, uh, er)
|
|
backchannel:
|
|
description: Non-lexical backchannel (mmhm, uh-huh)
|
|
|
|
# ---------------------------------------------------------------------------
|
|
# Incident Type
|
|
# ---------------------------------------------------------------------------
|
|
IncidentType:
|
|
description: |
|
|
Types of non-vocal incidents during speech.
|
|
Used on @type attribute of <incident> element.
|
|
permissible_values:
|
|
noise:
|
|
description: Non-human noise (traffic, machinery)
|
|
applause:
|
|
description: Audience applause
|
|
phone:
|
|
description: Phone ringing/notification
|
|
door:
|
|
description: Door opening/closing
|
|
footsteps:
|
|
description: Footsteps
|
|
paper:
|
|
description: Paper rustling
|
|
typing:
|
|
description: Typing sounds
|
|
music:
|
|
description: Background music
|
|
animal:
|
|
description: Animal sounds
|
|
interruption:
|
|
description: External interruption
|
|
technical:
|
|
description: Technical issue (microphone, recording)
|
|
|
|
# ---------------------------------------------------------------------------
|
|
# Kinesic Type
|
|
# ---------------------------------------------------------------------------
|
|
KinesicType:
|
|
description: |
|
|
Types of body language and gestures.
|
|
Used on @type attribute of <kinesic> element.
|
|
permissible_values:
|
|
nod:
|
|
description: Nodding
|
|
shake:
|
|
description: Head shaking
|
|
gesture:
|
|
description: Hand gesture
|
|
shrug:
|
|
description: Shoulder shrug
|
|
point:
|
|
description: Pointing
|
|
wave:
|
|
description: Waving
|
|
frown:
|
|
description: Frowning
|
|
smile:
|
|
description: Smiling
|
|
eye_contact:
|
|
description: Eye contact/gaze
|
|
posture:
|
|
description: Posture change
|
|
facial:
|
|
description: Facial expression
|
|
movement:
|
|
description: Body movement
|
|
|
|
# ---------------------------------------------------------------------------
|
|
# Pause Duration Category
|
|
# ---------------------------------------------------------------------------
|
|
PauseDurationCategory:
|
|
description: |
|
|
Categorical duration of pauses.
|
|
Alternative to numeric @dur attribute.
|
|
permissible_values:
|
|
short:
|
|
description: Short pause (< 0.5s)
|
|
medium:
|
|
description: Medium pause (0.5-2s)
|
|
long:
|
|
description: Long pause (2-5s)
|
|
very_long:
|
|
description: Very long pause (> 5s)
|
|
|
|
# ---------------------------------------------------------------------------
|
|
# Recording Type
|
|
# ---------------------------------------------------------------------------
|
|
RecordingType:
|
|
description: |
|
|
Types of audio/video recordings.
|
|
Used on @type attribute of <recording> element.
|
|
permissible_values:
|
|
audio:
|
|
description: Audio-only recording
|
|
video:
|
|
description: Video recording with audio
|
|
interview:
|
|
description: Interview recording
|
|
conversation:
|
|
description: Conversation recording
|
|
monologue:
|
|
description: Monologue/speech recording
|
|
broadcast:
|
|
description: Broadcast recording
|
|
field:
|
|
description: Field recording
|
|
studio:
|
|
description: Studio recording
|
|
phone:
|
|
description: Telephone recording
|
|
|
|
# ---------------------------------------------------------------------------
|
|
# Channel Mode
|
|
# ---------------------------------------------------------------------------
|
|
ChannelMode:
|
|
description: |
|
|
Mode of communication channel.
|
|
Extends header module's channel types for spoken texts.
|
|
permissible_values:
|
|
face_to_face:
|
|
description: Face-to-face conversation
|
|
telephone:
|
|
description: Telephone call
|
|
radio:
|
|
description: Radio broadcast
|
|
television:
|
|
description: Television broadcast
|
|
video_call:
|
|
description: Video conference call
|
|
podcast:
|
|
description: Podcast recording
|
|
lecture:
|
|
description: Lecture/presentation
|
|
|
|
# =============================================================================
|
|
# SLOTS (Attributes)
|
|
# =============================================================================
|
|
slots:
|
|
|
|
# ---------------------------------------------------------------------------
|
|
# Global TEI Attributes (shared)
|
|
# ---------------------------------------------------------------------------
|
|
xml_id:
|
|
description: Unique identifier for the element (xml:id)
|
|
range: string
|
|
slot_uri: tei:id
|
|
|
|
xml_lang:
|
|
description: Language of the element content (xml:lang)
|
|
range: string
|
|
slot_uri: tei:lang
|
|
|
|
# ---------------------------------------------------------------------------
|
|
# Speaker Identification (@who)
|
|
# ---------------------------------------------------------------------------
|
|
who:
|
|
description: |
|
|
Reference to the speaker producing this utterance.
|
|
Uses pointer to person/personGrp in the header.
|
|
range: uriorcurie
|
|
slot_uri: tei:who
|
|
|
|
# ---------------------------------------------------------------------------
|
|
# Temporal Alignment Attributes
|
|
# ---------------------------------------------------------------------------
|
|
start_ref:
|
|
description: |
|
|
Reference to starting synchronization point (@start).
|
|
Points to an anchor or when element for temporal alignment.
|
|
range: uriorcurie
|
|
slot_uri: tei:start
|
|
|
|
end_ref:
|
|
description: |
|
|
Reference to ending synchronization point (@end).
|
|
Points to an anchor or when element for temporal alignment.
|
|
range: uriorcurie
|
|
slot_uri: tei:end
|
|
|
|
synch:
|
|
description: |
|
|
References to synchronized elements (@synch).
|
|
Space-separated list of pointers to elements occurring simultaneously.
|
|
range: string
|
|
slot_uri: tei:synch
|
|
|
|
# ---------------------------------------------------------------------------
|
|
# Transition Attribute
|
|
# ---------------------------------------------------------------------------
|
|
trans:
|
|
description: |
|
|
Describes transition from previous utterance (@trans).
|
|
Values: smooth, pause, latching, overlap.
|
|
range: TransitionType
|
|
slot_uri: tei:trans
|
|
|
|
# ---------------------------------------------------------------------------
|
|
# Duration Attributes
|
|
# ---------------------------------------------------------------------------
|
|
dur:
|
|
description: |
|
|
Duration of element (@dur).
|
|
ISO 8601 duration format (e.g., PT1.5S for 1.5 seconds).
|
|
range: string
|
|
slot_uri: tei:dur
|
|
|
|
interval:
|
|
description: |
|
|
Time interval relative to origin (@interval).
|
|
Numeric value representing offset from timeline origin.
|
|
range: float
|
|
slot_uri: tei:interval
|
|
|
|
unit:
|
|
description: |
|
|
Unit of measurement for interval (@unit).
|
|
E.g., "s" for seconds, "ms" for milliseconds.
|
|
range: string
|
|
slot_uri: tei:unit
|
|
|
|
absolute:
|
|
description: |
|
|
Absolute timestamp (@absolute).
|
|
ISO 8601 dateTime for absolute temporal position.
|
|
range: string
|
|
slot_uri: tei:absolute
|
|
|
|
# ---------------------------------------------------------------------------
|
|
# Paralinguistic Shift Attributes
|
|
# ---------------------------------------------------------------------------
|
|
feature:
|
|
description: |
|
|
Paralinguistic feature being changed (@feature).
|
|
Values: tempo, loud, pitch, tension, rhythm, voice.
|
|
range: ParalinguisticFeatureType
|
|
slot_uri: tei:feature
|
|
|
|
new_value:
|
|
description: |
|
|
New state of paralinguistic feature (@new).
|
|
Value depends on feature type (e.g., "f" for loud feature).
|
|
range: string
|
|
slot_uri: tei:new
|
|
|
|
# ---------------------------------------------------------------------------
|
|
# Iterative/Gradual Attributes
|
|
# ---------------------------------------------------------------------------
|
|
iterated:
|
|
description: |
|
|
Whether sound/event is repeated (@iterated).
|
|
Boolean: true if the phenomenon repeats.
|
|
range: boolean
|
|
slot_uri: tei:iterated
|
|
|
|
gradual:
|
|
description: |
|
|
Whether shift is gradual (@gradual).
|
|
Boolean: true if feature changes gradually rather than suddenly.
|
|
range: boolean
|
|
slot_uri: tei:gradual
|
|
|
|
# ---------------------------------------------------------------------------
|
|
# Addressee Attribute
|
|
# ---------------------------------------------------------------------------
|
|
to_whom:
|
|
description: |
|
|
Reference to addressee(s) (@toWhom).
|
|
Pointer to person/personGrp being addressed.
|
|
range: uriorcurie
|
|
slot_uri: tei:toWhom
|
|
|
|
# =============================================================================
|
|
# CLASSES - UTTERANCE AND SPEECH ELEMENTS
|
|
# =============================================================================
|
|
classes:
|
|
|
|
# ---------------------------------------------------------------------------
|
|
# u (utterance) - Primary Speech Unit
|
|
# ---------------------------------------------------------------------------
|
|
Utterance:
|
|
class_uri: tei:u
|
|
description: |
|
|
Utterance (u) contains a stretch of speech usually preceded and
|
|
followed by silence or by a change of speaker. This is the primary
|
|
container for representing spoken contributions in transcription.
|
|
|
|
Key features:
|
|
- @who identifies the speaker (reference to person in header)
|
|
- @trans describes transition from previous utterance
|
|
- @start/@end provide temporal alignment
|
|
- May contain inline markup for pauses, vocals, incidents, etc.
|
|
|
|
TEI P5 Chapter 8.3.1 (Utterances)
|
|
slots:
|
|
- xml_id
|
|
- xml_lang
|
|
- who
|
|
- trans
|
|
- start_ref
|
|
- end_ref
|
|
attributes:
|
|
utterance_text:
|
|
description: The spoken text content
|
|
range: string
|
|
segments:
|
|
description: |
|
|
Child segments within the utterance.
|
|
Utterances may be subdivided into smaller segments.
|
|
range: SpeechSegment
|
|
multivalued: true
|
|
pauses:
|
|
description: Pauses within the utterance
|
|
range: Pause
|
|
multivalued: true
|
|
vocals:
|
|
description: Vocal sounds within the utterance
|
|
range: Vocal
|
|
multivalued: true
|
|
incidents:
|
|
description: Non-vocal incidents during the utterance
|
|
range: Incident
|
|
multivalued: true
|
|
kinesics:
|
|
description: Body language/gestures during the utterance
|
|
range: Kinesic
|
|
multivalued: true
|
|
shifts:
|
|
description: Paralinguistic shifts within the utterance
|
|
range: Shift
|
|
multivalued: true
|
|
unclear_spans:
|
|
description: Unclear/inaudible passages
|
|
range: Unclear
|
|
multivalued: true
|
|
gap_markers:
|
|
description: Gaps in transcription
|
|
range: GapSpoken
|
|
multivalued: true
|
|
exact_mappings:
|
|
- crm:E33_Linguistic_Object
|
|
- schema:SpeakAction
|
|
annotations:
|
|
tei_element: u
|
|
tei_module: spoken
|
|
glam_hypernym: TXT.SPK
|
|
|
|
# ---------------------------------------------------------------------------
|
|
# seg (speech segment)
|
|
# ---------------------------------------------------------------------------
|
|
SpeechSegment:
|
|
class_uri: tei:seg
|
|
description: |
|
|
Speech segment (seg) represents an arbitrary segmentation of text
|
|
below the utterance level. Can be used for intonation units, tone
|
|
groups, or other linguistic segments within spoken text.
|
|
|
|
TEI P5 Chapter 8.4.4 (Blocks, Segments, and Anchors)
|
|
slots:
|
|
- xml_id
|
|
- xml_lang
|
|
- start_ref
|
|
- end_ref
|
|
attributes:
|
|
segment_text:
|
|
description: The text content of the segment
|
|
range: string
|
|
segment_type:
|
|
description: Type of segment (intonation_unit, tone_group, etc.)
|
|
range: string
|
|
segment_function:
|
|
description: Pragmatic function of the segment
|
|
range: string
|
|
exact_mappings:
|
|
- crm:E33_Linguistic_Object
|
|
annotations:
|
|
tei_element: seg
|
|
tei_module: linking
|
|
glam_hypernym: TXT.SPK
|
|
|
|
# ---------------------------------------------------------------------------
|
|
# pause - Pause in Speech
|
|
# ---------------------------------------------------------------------------
|
|
Pause:
|
|
class_uri: tei:pause
|
|
description: |
|
|
Pause (pause) marks a pause either between or within utterances.
|
|
May specify duration using @dur attribute (ISO 8601 duration) or
|
|
categorical duration via type.
|
|
|
|
TEI P5 Chapter 8.3.4 (Pausing)
|
|
slots:
|
|
- xml_id
|
|
- who
|
|
- dur
|
|
attributes:
|
|
pause_type:
|
|
description: Categorical description of pause duration
|
|
range: PauseDurationCategory
|
|
measured_duration:
|
|
description: Measured duration in seconds (if available)
|
|
range: float
|
|
exact_mappings:
|
|
- crm:E52_Time-Span
|
|
annotations:
|
|
tei_element: pause
|
|
tei_module: spoken
|
|
glam_hypernym: TMP.DUR
|
|
|
|
# ---------------------------------------------------------------------------
|
|
# vocal - Vocal Sounds
|
|
# ---------------------------------------------------------------------------
|
|
Vocal:
|
|
class_uri: tei:vocal
|
|
description: |
|
|
Vocal (vocal) marks any vocalized but not necessarily lexical
|
|
phenomenon, such as voiced pauses, laughter, coughing, non-lexical
|
|
backchannels, and other vocal sounds.
|
|
|
|
TEI P5 Chapter 8.3.3 (Vocal, Kinesic, Incident)
|
|
slots:
|
|
- xml_id
|
|
- who
|
|
- dur
|
|
- iterated
|
|
attributes:
|
|
vocal_type:
|
|
description: Type of vocal sound
|
|
range: VocalSoundType
|
|
vocal_description:
|
|
description: Free-text description of the vocal sound
|
|
range: string
|
|
exact_mappings:
|
|
- crm:E7_Activity
|
|
annotations:
|
|
tei_element: vocal
|
|
tei_module: spoken
|
|
glam_hypernym: TXT.SPK.VOC
|
|
|
|
# ---------------------------------------------------------------------------
|
|
# incident - Non-vocal Events
|
|
# ---------------------------------------------------------------------------
|
|
Incident:
|
|
class_uri: tei:incident
|
|
description: |
|
|
Incident (incident) marks any phenomenon or occurrence, not
|
|
necessarily vocalized or communicative, such as incidental noises
|
|
or other events affecting communication.
|
|
|
|
TEI P5 Chapter 8.3.3 (Vocal, Kinesic, Incident)
|
|
slots:
|
|
- xml_id
|
|
- who
|
|
- dur
|
|
attributes:
|
|
incident_type:
|
|
description: Type of incident
|
|
range: IncidentType
|
|
incident_description:
|
|
description: Free-text description of the incident
|
|
range: string
|
|
exact_mappings:
|
|
- crm:E5_Event
|
|
annotations:
|
|
tei_element: incident
|
|
tei_module: spoken
|
|
glam_hypernym: TMP.EVT.INC
|
|
|
|
# ---------------------------------------------------------------------------
|
|
# kinesic - Body Language/Gestures
|
|
# ---------------------------------------------------------------------------
|
|
Kinesic:
|
|
class_uri: tei:kinesic
|
|
description: |
|
|
Kinesic (kinesic) marks any communicative phenomenon, not
|
|
necessarily vocalized, such as gestures, facial expressions,
|
|
posture changes, and other body language.
|
|
|
|
TEI P5 Chapter 8.3.3 (Vocal, Kinesic, Incident)
|
|
slots:
|
|
- xml_id
|
|
- who
|
|
- dur
|
|
- iterated
|
|
attributes:
|
|
kinesic_type:
|
|
description: Type of body language/gesture
|
|
range: KinesicType
|
|
kinesic_description:
|
|
description: Free-text description of the kinesic event
|
|
range: string
|
|
exact_mappings:
|
|
- crm:E7_Activity
|
|
annotations:
|
|
tei_element: kinesic
|
|
tei_module: spoken
|
|
glam_hypernym: TXT.SPK.KIN
|
|
|
|
# ---------------------------------------------------------------------------
|
|
# shift - Paralinguistic Feature Change
|
|
# ---------------------------------------------------------------------------
|
|
Shift:
|
|
class_uri: tei:shift
|
|
description: |
|
|
Shift (shift) marks the point at which some paralinguistic feature
|
|
of a series of utterances by any one speaker changes. This includes
|
|
changes in tempo, loudness, pitch, tension, rhythm, or voice quality.
|
|
|
|
The feature change is understood to apply to all subsequent
|
|
utterances by the same speaker until changed by another shift.
|
|
|
|
TEI P5 Chapter 8.3.5 (Shifts)
|
|
slots:
|
|
- xml_id
|
|
- who
|
|
- feature
|
|
- new_value
|
|
- gradual
|
|
attributes:
|
|
shift_description:
|
|
description: Free-text description of the shift
|
|
range: string
|
|
exact_mappings:
|
|
- crm:E13_Attribute_Assignment
|
|
annotations:
|
|
tei_element: shift
|
|
tei_module: spoken
|
|
glam_hypernym: TXT.SPK.PAR
|
|
|
|
# ---------------------------------------------------------------------------
|
|
# writing - Written Text in Spoken Context
|
|
# ---------------------------------------------------------------------------
|
|
Writing:
|
|
class_uri: tei:writing
|
|
description: |
|
|
Writing (writing) contains a passage of written text revealed to
|
|
participants in the course of a spoken text, such as a sign being
|
|
read aloud, a written question, or projected slides.
|
|
|
|
TEI P5 Chapter 8.3.6 (Writing)
|
|
slots:
|
|
- xml_id
|
|
- who
|
|
attributes:
|
|
writing_text:
|
|
description: The written text content
|
|
range: string
|
|
writing_type:
|
|
description: Type of writing (sign, slide, document, etc.)
|
|
range: string
|
|
writing_source:
|
|
description: Source of the written text
|
|
range: string
|
|
exact_mappings:
|
|
- crm:E33_Linguistic_Object
|
|
annotations:
|
|
tei_element: writing
|
|
tei_module: spoken
|
|
glam_hypernym: TXT.WRT
|
|
|
|
# ---------------------------------------------------------------------------
|
|
# unclear - Inaudible/Unclear Speech
|
|
# ---------------------------------------------------------------------------
|
|
Unclear:
|
|
class_uri: tei:unclear
|
|
description: |
|
|
Unclear (unclear) contains a word, phrase, or passage which cannot
|
|
be transcribed with certainty because it is illegible or inaudible
|
|
in the source recording.
|
|
|
|
TEI P5 Chapter 11.3.3.1 (Damage, Illegibility, and Supplied Text)
|
|
slots:
|
|
- xml_id
|
|
- who
|
|
attributes:
|
|
unclear_text:
|
|
description: Best-guess transcription of unclear content
|
|
range: string
|
|
unclear_reason:
|
|
description: Reason for uncertainty (noise, overlap, mumbling)
|
|
range: string
|
|
certainty:
|
|
description: Degree of certainty (high, medium, low)
|
|
range: string
|
|
agent_resp:
|
|
description: Person/agent responsible for transcription
|
|
range: uriorcurie
|
|
exact_mappings:
|
|
- crm:E33_Linguistic_Object
|
|
annotations:
|
|
tei_element: unclear
|
|
tei_module: core
|
|
glam_hypernym: TXT.SPK.UNC
|
|
|
|
# ---------------------------------------------------------------------------
|
|
# gap - Omission in Transcription
|
|
# ---------------------------------------------------------------------------
|
|
GapSpoken:
|
|
class_uri: tei:gap
|
|
description: |
|
|
Gap (gap) indicates a point where material has been omitted in
|
|
a transcription. In spoken texts, this may be due to inaudibility,
|
|
equipment failure, or editorial omission.
|
|
|
|
TEI P5 Chapter 3.5.3 (Additions, Deletions, and Omissions)
|
|
slots:
|
|
- xml_id
|
|
- dur
|
|
attributes:
|
|
gap_reason:
|
|
description: Reason for omission (inaudible, equipment, editorial)
|
|
range: string
|
|
gap_extent:
|
|
description: Estimated extent of omitted material
|
|
range: string
|
|
gap_agent:
|
|
description: Agent responsible for omission
|
|
range: uriorcurie
|
|
exact_mappings:
|
|
- crm:E79_Part_Removal
|
|
annotations:
|
|
tei_element: gap
|
|
tei_module: core
|
|
glam_hypernym: TXT.GAP
|
|
|
|
# =============================================================================
|
|
# CLASSES - TEMPORAL ALIGNMENT ELEMENTS
|
|
# =============================================================================
|
|
|
|
# ---------------------------------------------------------------------------
|
|
# timeline - Temporal Structure
|
|
# ---------------------------------------------------------------------------
|
|
Timeline:
|
|
class_uri: tei:timeline
|
|
description: |
|
|
Timeline (timeline) provides a set of ordered points in time which
|
|
can be linked to elements of a spoken text to create a temporal
|
|
alignment. Essential for synchronizing transcription with audio/video.
|
|
|
|
TEI P5 Chapter 8.4.5 (Synchronization and Overlap)
|
|
slots:
|
|
- xml_id
|
|
attributes:
|
|
origin_ref:
|
|
description: Reference to the origin point (@origin)
|
|
range: uriorcurie
|
|
timeline_unit:
|
|
description: Default unit for time intervals
|
|
range: string
|
|
when_points:
|
|
description: Time points in this timeline
|
|
range: When
|
|
multivalued: true
|
|
required: true
|
|
exact_mappings:
|
|
- crm:E52_Time-Span
|
|
annotations:
|
|
tei_element: timeline
|
|
tei_module: spoken
|
|
glam_hypernym: TMP.TLN
|
|
|
|
# ---------------------------------------------------------------------------
|
|
# when - Time Point
|
|
# ---------------------------------------------------------------------------
|
|
When:
|
|
class_uri: tei:when
|
|
description: |
|
|
When (when) indicates a point in time either relative to other
|
|
elements in the same timeline, or absolutely using timestamps.
|
|
Used for temporal alignment of utterances and events.
|
|
|
|
TEI P5 Chapter 8.4.5 (Synchronization and Overlap)
|
|
slots:
|
|
- xml_id
|
|
- synch
|
|
- interval
|
|
- unit
|
|
- absolute
|
|
attributes:
|
|
since_ref:
|
|
description: Reference to preceding when element (@since)
|
|
range: uriorcurie
|
|
exact_mappings:
|
|
- crm:E61_Time_Primitive
|
|
- time:Instant
|
|
annotations:
|
|
tei_element: when
|
|
tei_module: spoken
|
|
glam_hypernym: TMP.PNT
|
|
|
|
# =============================================================================
|
|
# CLASSES - RECORDING METADATA ELEMENTS
|
|
# =============================================================================
|
|
|
|
# ---------------------------------------------------------------------------
|
|
# recordingStmt - Recording Statement
|
|
# ---------------------------------------------------------------------------
|
|
RecordingStmt:
|
|
class_uri: tei:recordingStmt
|
|
description: |
|
|
Recording statement (recordingStmt) describes a set of recordings
|
|
used as the basis for transcription of a spoken text. Container
|
|
for one or more recording elements in the header.
|
|
|
|
TEI P5 Chapter 8.2 (Documenting the Source of Transcribed Speech)
|
|
slots:
|
|
- xml_id
|
|
attributes:
|
|
recordings:
|
|
description: Recording events documented
|
|
range: Recording
|
|
multivalued: true
|
|
required: true
|
|
annotations:
|
|
tei_element: recordingStmt
|
|
tei_module: spoken
|
|
glam_hypernym: DOC.MET
|
|
|
|
# ---------------------------------------------------------------------------
|
|
# recording - Recording Event
|
|
# ---------------------------------------------------------------------------
|
|
Recording:
|
|
class_uri: tei:recording
|
|
description: |
|
|
Recording (recording) provides details of an audio or video
|
|
recording event used as the source of a spoken text, either
|
|
directly or from a public broadcast.
|
|
|
|
TEI P5 Chapter 8.2 (Documenting the Source of Transcribed Speech)
|
|
slots:
|
|
- xml_id
|
|
- dur
|
|
attributes:
|
|
recording_type:
|
|
description: Type of recording (audio, video, etc.)
|
|
range: RecordingType
|
|
recording_date:
|
|
description: Date of recording
|
|
range: string
|
|
equipment_info:
|
|
description: Recording equipment details
|
|
range: Equipment
|
|
respStmt:
|
|
description: Person/org responsible for recording
|
|
range: string
|
|
broadcast_info:
|
|
description: Broadcast source (if from broadcast)
|
|
range: Broadcast
|
|
exact_mappings:
|
|
- crm:E65_Creation
|
|
- schema:VideoObject
|
|
- schema:AudioObject
|
|
annotations:
|
|
tei_element: recording
|
|
tei_module: spoken
|
|
glam_hypernym: THG.REC
|
|
|
|
# ---------------------------------------------------------------------------
|
|
# broadcast - Broadcast Source
|
|
# ---------------------------------------------------------------------------
|
|
Broadcast:
|
|
class_uri: tei:broadcast
|
|
description: |
|
|
Broadcast (broadcast) describes a broadcast used as the source
|
|
of a spoken text. Includes information about the broadcasting
|
|
organization, channel, date, and program.
|
|
|
|
TEI P5 Chapter 8.2 (Documenting the Source of Transcribed Speech)
|
|
slots:
|
|
- xml_id
|
|
attributes:
|
|
broadcast_bibl:
|
|
description: Bibliographic reference to broadcast
|
|
range: string
|
|
broadcaster:
|
|
description: Broadcasting organization
|
|
range: string
|
|
channel_name:
|
|
description: Broadcast channel name
|
|
range: string
|
|
broadcast_date:
|
|
description: Date and time of broadcast
|
|
range: string
|
|
program_title:
|
|
description: Title of broadcast program
|
|
range: string
|
|
exact_mappings:
|
|
- schema:BroadcastEvent
|
|
annotations:
|
|
tei_element: broadcast
|
|
tei_module: spoken
|
|
glam_hypernym: TMP.EVT.BRC
|
|
|
|
# ---------------------------------------------------------------------------
|
|
# equipment - Recording Equipment
|
|
# ---------------------------------------------------------------------------
|
|
Equipment:
|
|
class_uri: tei:equipment
|
|
description: |
|
|
Equipment (equipment) provides technical details of the equipment
|
|
and calculation conditions relevant to the creation of a spoken
|
|
text transcription.
|
|
|
|
TEI P5 Chapter 8.2 (Documenting the Source of Transcribed Speech)
|
|
slots:
|
|
- xml_id
|
|
attributes:
|
|
equipment_desc:
|
|
description: Description of recording equipment
|
|
range: string
|
|
microphone_type:
|
|
description: Type of microphone used
|
|
range: string
|
|
recorder_model:
|
|
description: Recording device model
|
|
range: string
|
|
format_info:
|
|
description: Audio/video format information
|
|
range: string
|
|
sample_rate:
|
|
description: Audio sample rate (e.g., 44100 Hz)
|
|
range: string
|
|
annotations:
|
|
tei_element: equipment
|
|
tei_module: spoken
|
|
glam_hypernym: THG.EQP
|
|
|
|
# ---------------------------------------------------------------------------
|
|
# scriptStmt - Script Statement
|
|
# ---------------------------------------------------------------------------
|
|
ScriptStmt:
|
|
class_uri: tei:scriptStmt
|
|
description: |
|
|
Script statement (scriptStmt) contains a citation giving details
|
|
of the script used for a spoken text. Applies when the spoken
|
|
text follows a prepared script.
|
|
|
|
TEI P5 Chapter 8.2 (Documenting the Source of Transcribed Speech)
|
|
slots:
|
|
- xml_id
|
|
attributes:
|
|
script_bibl:
|
|
description: Bibliographic reference to script
|
|
range: string
|
|
annotations:
|
|
tei_element: scriptStmt
|
|
tei_module: spoken
|
|
glam_hypernym: WRK
|
|
|
|
# ---------------------------------------------------------------------------
|
|
# transcriptionDesc - Transcription Description
|
|
# ---------------------------------------------------------------------------
|
|
TranscriptionDesc:
|
|
class_uri: tei:transcriptionDesc
|
|
description: |
|
|
Transcription description (transcriptionDesc) describes the set
|
|
of transcription conventions used, particularly useful for
|
|
documenting phonetic transcription systems or specialized notation.
|
|
|
|
TEI P5 Chapter 8.2 (Documenting the Source of Transcribed Speech)
|
|
slots:
|
|
- xml_id
|
|
attributes:
|
|
ident:
|
|
description: Identifier for transcription system
|
|
range: string
|
|
transcription_version:
|
|
description: Version of transcription system
|
|
range: string
|
|
transcription_url:
|
|
description: URL describing transcription conventions
|
|
range: uriorcurie
|
|
transcription_desc:
|
|
description: Description of transcription conventions
|
|
range: string
|
|
annotations:
|
|
tei_element: transcriptionDesc
|
|
tei_module: spoken
|
|
glam_hypernym: DOC.MET
|
|
|
|
# =============================================================================
|
|
# GLAM-NER HYPERNYM MAPPINGS SUMMARY
|
|
# =============================================================================
|
|
#
|
|
# This module covers spoken text transcription from TEI Chapter 8.
|
|
# Primary GLAM-NER hypernym mappings:
|
|
#
|
|
# TXT.SPK (Spoken Text):
|
|
# - Utterance (u) - Main speech unit
|
|
# - SpeechSegment (seg) - Subdivisions
|
|
# - Unclear - Unclear/inaudible speech
|
|
#
|
|
# TXT.SPK.VOC (Vocal Sounds):
|
|
# - Vocal - Non-lexical vocalizations
|
|
#
|
|
# TXT.SPK.KIN (Kinesics):
|
|
# - Kinesic - Body language, gestures
|
|
#
|
|
# TXT.SPK.PAR (Paralinguistic Features):
|
|
# - Shift - Changes in tempo, loudness, pitch, etc.
|
|
#
|
|
# TXT.WRT (Written Text):
|
|
# - Writing - Written text in spoken context
|
|
#
|
|
# TMP.DUR (Duration):
|
|
# - Pause - Pauses in speech
|
|
#
|
|
# TMP.EVT (Events):
|
|
# - Incident - Non-vocal events
|
|
# - Broadcast - Broadcast events
|
|
#
|
|
# TMP.TLN (Timeline):
|
|
# - Timeline - Temporal alignment structure
|
|
#
|
|
# TMP.PNT (Time Point):
|
|
# - When - Synchronization point
|
|
#
|
|
# THG.REC (Recording):
|
|
# - Recording - Audio/video recording
|
|
#
|
|
# THG.EQP (Equipment):
|
|
# - Equipment - Recording equipment
|
|
#
|
|
# DOC.MET (Document Metadata):
|
|
# - RecordingStmt, TranscriptionDesc
|
|
#
|
|
# WRK (Work):
|
|
# - ScriptStmt - Script reference
|
|
#
|
|
# =============================================================================
|
|
# ONTOLOGY MAPPINGS
|
|
# =============================================================================
|
|
#
|
|
# CIDOC-CRM:
|
|
# - Utterance → crm:E33_Linguistic_Object
|
|
# - Vocal, Kinesic → crm:E7_Activity
|
|
# - Incident → crm:E5_Event
|
|
# - Pause, Timeline → crm:E52_Time-Span
|
|
# - When → crm:E61_Time_Primitive
|
|
# - Shift → crm:E13_Attribute_Assignment
|
|
# - Recording → crm:E65_Creation
|
|
# - GapSpoken → crm:E79_Part_Removal
|
|
#
|
|
# Schema.org:
|
|
# - Utterance → schema:SpeakAction
|
|
# - Recording → schema:VideoObject/AudioObject
|
|
# - Broadcast → schema:BroadcastEvent
|
|
#
|
|
# W3C Time Ontology:
|
|
# - When → time:Instant
|
|
#
|
|
# PROV-O (Provenance):
|
|
# - Recording → prov:Activity
|
|
#
|
|
# =============================================================================
|
|
# USAGE NOTES
|
|
# =============================================================================
|
|
#
|
|
# Spoken text transcription is used for:
|
|
# 1. Oral history archives (heritage institutions)
|
|
# 2. Sociolinguistic research
|
|
# 3. Discourse analysis
|
|
# 4. Documentary filmmaking transcription
|
|
# 5. Legal proceedings transcription
|
|
# 6. Podcast/broadcast archiving
|
|
# 7. Sign language documentation (kinesic)
|
|
#
|
|
# Key patterns:
|
|
# - <u who="#speaker1"> wraps speech from identified speakers
|
|
# - <pause/> marks pauses with optional duration
|
|
# - <vocal type="laughter"/> marks non-lexical sounds
|
|
# - <incident type="noise"/> marks external events
|
|
# - <kinesic type="nod"/> marks body language
|
|
# - <shift feature="loud" new="f"/> marks paralinguistic changes
|
|
# - <timeline>/<when> provides temporal alignment with audio/video
|
|
# - <recording>/<recordingStmt> documents source recordings
|
|
#
|
|
# Integration with NER:
|
|
# - Speaker names in @who → AGT.PER (via header's listPerson)
|
|
# - Place names in utterances → GEO
|
|
# - Date references → TMP.DAT
|
|
# - Organization names → GRP.ORG
|
|
# - Broadcast information → TMP.EVT.BRC
|
|
#
|
|
# Heritage Institution Applications:
|
|
# - Oral history collections transcription
|
|
# - Museum audio guide scripts
|
|
# - Archive interview transcriptions
|
|
# - Documentary film annotation
|
|
# - Radio/TV broadcast archives
|
|
#
|
|
# =============================================================================
|
|
# VERSION HISTORY
|
|
# =============================================================================
|
|
#
|
|
# Version 1.0.0 (2025-12-03):
|
|
# - Initial release covering TEI P5 Chapter 8 (Transcriptions of Speech)
|
|
# - 18 class definitions for spoken text elements
|
|
# - 10 enum definitions for classification
|
|
# - Ontology mappings to CIDOC-CRM, Schema.org, W3C Time
|
|
# - GLAM-NER hypernym annotations for all relevant elements
|
|
# - Temporal alignment support (timeline, when)
|
|
# - Recording metadata support (recordingStmt, recording, equipment)
|
|
# - Paralinguistic feature tracking (shift)
|
|
#
|
|
# =============================================================================
|
|
|