mfrebo/align-vandam: YODA repo to align vandam corpus using Montreal Forced Aligner. @ 707d897fcfe2933cf136394c824de679ffc8928e

YODA repo to align vandam corpus using Montreal Forced Aligner.

mfrebo 707d897fcf Add 'LICENSE'		2 年之前
.datalad	c11e500a15 [DATALAD] new dataset	2 年之前
.vscode	385198801d corrected with lucas' review	2 年之前
code	dbd9efcf3f updated compare.py + confusion matrices	2 年之前
inputs	2cb46a39ea cleaned unnecessary files	2 年之前
outputs	dbd9efcf3f updated compare.py + confusion matrices	2 年之前
.gitattributes	c84fb1c33e Apply YODA dataset setup	2 年之前
.gitmodules	1d2b1741b5 [DATALAD] Recorded changes	2 年之前
CHANGELOG.md	c84fb1c33e Apply YODA dataset setup	2 年之前
Comparison-summary.md	17093d6efb edited comaprison.md	2 年之前
LICENSE	707d897fcf Add 'LICENSE'	2 年之前
README.md	2820fd10b6 modified readme	2 年之前
datacite.yml	dedb8732a6 Add information for publishing with DataCite	2 年之前

		
				README.md
			
				Project 

Dataset structure

All inputs (i.e. building blocks from other sources) are located in
inputs/.
All custom code is located in code/.

Steps to generate aligned .csv from vandam-data .cha annotations

Run code/csv2grid with annotations/cha/converted as input (converts the original .csv to .TextGrid)
Run MFA Align with output files of previous step as input (with inputs/mfa-models/acoustic & inputs/mfa-models/dictionary as required)
Run code/grid2csv to convert .TextGrids to .csv with outputs of previous step as input.

Steps for comparison of aligned segments with human annotator

Use child-project sampler to generate 5x 1 minute segments (high-volubility) and outputs them in outputs/
Use child-project eaf-builder with files generated at previous step and templates at inputs/eaf_templates
Annotate segments by hand on ELAN
Create csv dataframe with each segment in outputs/fivesegments-eaf
Import that .csv with child-project import-annotations

datacite.yml
Title	Alignment of Vandam corpus using Montreal Forced Aligner
Authors	FREBOURG,Martin;McGill University Gautheron,Lucas;École Normale Supérieure - PSL Cristia,Alejandrina;École Normale Supérieure - PSL
Description	YODA repo to align vandam corpus using Montreal Forced Aligner (MFA).
License	Apache License 2.0 (https://www.apache.org/licenses/LICENSE-2.0)
References	Citation1 [doi:10.xxx/zzzz] (IsSupplementTo) Citation2 [arxiv:mmmm.nnnn] (IsSupplementTo) Citation3 [pmid:nnnnnnnn] (IsReferencedBy)
Funding	DFG, AB1234/5-6 EU, EU.12345
Keywords	Neuroscience Linguistics Vandam Montreal Forced Aligner MFA annotations
Resource Type	Dataset