37.2802, Software: TAPA (Toolkit for Acoustic-Phonetic Analysis)

[The LINGUIST List]

LINGUIST List: Vol-37-2802. Wed Sep 02 2026. ISSN: 1069 - 4875.

Subject: 37.2802, Software: TAPA (Toolkit for Acoustic-Phonetic Analysis)

Moderator: Steven Moran (linguist at linguistlist.org)
Managing Editor: Valeriia Vyshnevetska
Team: Helen Aristar-Dry, Daniel Swanson
Jobs: jobs at linguistlist.org | Conferences: callconf at linguistlist.org | Pubs: pubs at linguistlist.org

Homepage: http://linguistlist.org

Editor for this issue: Daniel Swanson <daniel at linguistlist.org>

================================================================


Date: 01-Sep-2026
From: Ethan Kutlu [ethan-kutlu at uiowa.edu]
Subject: TAPA (Toolkit for Acoustic-Phonetic Analysis)


I am writing to share TAPA (Toolkit for Acoustic-Phonetic Analysis),
an open-source pipeline for extracting acoustic-phonetic measurements
from naturalistic, multi-speaker audio. The accompanying paper has
been accepted for publication in Behavior Research Methods.
 
Analyzing a single recording can be laborious. For researchers working
with long-form audio, or without a team of trained annotators, that
cost is out of reach, and current funding conditions have made the
bottleneck more pronounced.
 
TAPA links the stages of a standard acoustic-phonetic workflow, each
usable independently or replaceable with an alternative: audio
acquisition (from YouTube if needed), voice activity detection,
speaker diarization, transcription, forced alignment, vowel formants,
stop voice onset time, and fricative spectral moments. Output is
written as JSON and CSV, with a run summary recording which component
produced each measurement.
 
We name the toolkit TAPA inspired by the tapas culture. What starts as
sharing a meal made of small bites leads to long term relationships
and community building. We hope that TAPA can bring communities
together with the same spirit. 
 
Our manuscript reports validation against expert hand-coding on a
90-minute multi-speaker recording, downloaded directly from YouTube.
We want to highlight that TAPA is a tool, not a replacement for a
trained phonetician. Every measurement requires oversight. The current
release was validated on adult American English in a single recording
context. We are actively testing the toolkit with clinical
populations, developmental samples, and bilingual speech, and will
post updates on our Github moving forward. We welcome collaboration or
feedback from anyone working in these areas.
 
The toolkit is open-source, runs locally, and transmits no data
externally. Please note that the Google Colab version is not local if
you choose that route. 
 
Code: https://github.com/sarmadchandio/tapa
Preprint: https://zenodo.org/records/22236237
 
I am more than happy to provide a live tutorial for interested labs or
departments! Please feel free to get in touch.

Linguistic Field(s): Computational Linguistics
                     Phonetics




------------------------------------------------------------------------------

********************** LINGUIST List Support ***********************
Please consider donating to the Linguist List, a U.S. 501(c)(3) not for profit organization:

https://www.paypal.com/donate/?hosted_button_id=87C2AXTVC4PP8

LINGUIST List is supported by the following publishers:

Australian Linguistics Society https://als.asn.au/Home

Bloomsbury Publishing http://www.bloomsbury.com/uk/

Cambridge University Press http://www.cambridge.org/linguistics

Cascadilla Press http://www.cascadilla.com/

De Gruyter Brill https://www.degruyterbrill.com/?changeLang=en

Edinburgh University Press http://www.edinburghuniversitypress.com

European Language Resources Association (ELRA) http://www.elra.info

John Benjamins http://www.benjamins.com/

Language Science Press http://langsci-press.org

Lincom GmbH https://lincom-shop.eu/

MDPI Languages https://www.mdpi.com/journal/languages

MIT Press http://mitpress.mit.edu/

Multilingual Matters http://www.multilingual-matters.com/

Narr Francke Attempto Verlag GmbH + Co. KG http://www.narr.de/

Netherlands Graduate School of Linguistics / Landelijke (LOT) http://www.lotpublications.nl/

Peter Lang AG http://www.peterlang.com

SIL International Publications http://www.sil.org/resources/publications


----------------------------------------------------------
LINGUIST List: Vol-37-2802
----------------------------------------------------------