nzilbb.formatter.praat (2.7.4)

Serializer/Deserializer for Praat TextGrids.

When parsing a Praat TextGrid, the general assumption is that each TextGrid tier corresponds to an annotation layer, and before being fully processed, correspondences between tiers and layers need to be specified. The formatter tries to select sensible defaults for these correspondences; as a general rule, if the name of the tier matches the name of an existing annotation layer, then the tier will be mapped to the layer with the same name.

If no automatic correspondence is obvious, the formatter assumes that interval tiers contain the transcript of the speech of one speaker; the tier is mapped to the “utterance” layer, and the speaker's name/ID is assumed to be the name of the tier.

While determining default tier-to-layer mappings, the following special cases also apply:

tiers named lines or utterance[s] are mapped to the utterance layer.
tiers named speaker[s], turn[s], or “utterances” are mapped to the turn (speaker turn) layer.
tiers named ORT[-…] or word[…] are mapped to the word layer.
tiers named mfa, phone[s][...], or MAU[-…], are mapped to the segment (phone) layer.

TextGrid Structure

Assuming the TextGrid is a transcript, the speaker of each utterance in the TextGrid must be systematically identifiable. There are two possible structures for the TextGrid to facilitate this:

One tier per speaker, tier name = speaker name
Turns tier and utterances tier, turns tier containing speaker names

Transcription Conventions

Praat has no direct mechanism for marking non-speech annotations in their position within the transcript text. However, LaBB-CAT supports the use of textual conventions in various ways to make certain annotations:

To tag a word with its pronunciation, enter the pronunciation in square brackets (with no spaces), directly following the word (i.e. with no intervening space), e.g.:
…this was at Wingatui[wIN@tui]…
To tag a word with its full orthography (if the transcript doesn't include it), enter the orthography (with no spaces) in round parentheses, directly following the word (i.e. with no intervening space), e.g.:
…I can't remem~(remember)…
To insert a noise annotation within the text, enclose it in square brackets (surrounded by spaces so it's not taken as a pronunciation annotation), e.g.:
…sometimes me [laughs] not always but sometimes…
To insert a comment annotation within the text, enclose it in curly braces (surrounded by spaces), e.g.:
…beautifully warm {softly} but its…

Configuration

The following parameters can be specified for the formatter:

useConventions: true to use transcript conventions to identify comment, noise, lexical and pronuncation annotations. (see Transcription Conventions).
commentLayer: ID of layer for commentary (see Transcription Conventions),
noiseLayer: ID of layer for background/non-verbal noises (see Transcription Conventions).
lexicalLayer: ID of layer for lexical tags which identify to lexical item if the token orthography doesn't do so (see Transcription Conventions).
pronounceLayer: ID of layer for manual pronunciation tags (see Transcription Conventions).
renameShortNumericSpeakers: If true, short speaker names like ‘S1’ will be prefixed with the transcript name during import.
allowPeerOverlap: If true, allows TextGrids with, for example, multiple segment tiers, if the underlying annotations are invalid and have overlapping segments.
utteranceThreshold: Minimum inter-word pause (in seconds) to trigger an utterance boundary, when no utterance layer is mapped. 0 means ‘do not infer utterance boundaries’.
ignoreLabels: Regular expression for annotation to ignore, e.g. <p:> to ignore MAUS pauses.