Automated Alignment and Vowel Extraction with Manual Transcriptions

Upload your audio files with manual transcriptions to run forced alignment using ProsodyLab Aligner, followed by formant extraction with FAVE-extract.

Please be sure that your transcriptions are in plain text, with no special characters and preferably no punctuation, as described here. DARLA tries to handle these cases, but you will reduce the chance of errors if you clean up your files as described.

Click here at any time to cancel or start over.

Upload a .wav or .mp3 file:
Longer recordings (of at least 2 minutes) are recommended. Your uploaded files are stored temporarily on the Dartmouth servers in order to process your job, and deleted after.

Manual transcription as a .txt file:
We recommend creating this file using Notepad or TextEdit (with smart replace turned off) or emacs or any other plaintext editor. Transcripts created by "rich text" editors like Word may contain markup that will interfere with your results.

Filter out stop-words? Yes No
This is the list of stop-words we remove. (Link opens in a new tab.)

Filter out unstressed vowels? Yes No

Filter out vowels whose F1 or F2 bandwidths are over 300? Yes No

Your e-mail address:
We will not store or distribute your address.