Toolkit for acoustic-phonetic analysis of naturalistic speech data

Ethan Kutlu; Emerson Peters; Ciara Tapanes; Sarmad Chandio; Osama Khalid

doi:10.3758/s13428-026-03174-y

Back

Toolkit for acoustic-phonetic analysis of naturalistic speech data

Journal article

Open access

Peer reviewed

Toolkit for acoustic-phonetic analysis of naturalistic speech data

Ethan Kutlu, Emerson Peters, Ciara Tapanes, Sarmad Chandio and Osama Khalid

Behavior research methods, Vol.58(10), 289

09/09/2026

DOI: 10.3758/s13428-026-03174-y

PMCID: PMC13558450

PMID: 42717133

Appears in UI Libraries Support Open Access

Files and links (1)

url

https://doi.org/10.3758/s13428-026-03174-yView

Published (Version of record) Open Access

Abstract

A major limitation in the speech sciences is access to naturalistic data in experimental settings and the difficulty of translating laboratory designs to real-world contexts. Researchers studying speech production or perception often rely on in-lab recordings, which constrain the sociolinguistic contexts examined and limit ecological validity. The Toolkit for Acoustic-Phonetic Analysis (TAPA) is an open-source pipeline that automates the acquisition, transcription, speaker diarization, forced alignment, and per-segment acoustic analysis of naturalistic, single/multi-speaker audio. The current release supports vowel formant extraction, stop voice onset time, and fricative spectral moments. We demonstrate TAPA on the 2016 U.S. presidential debate, extracting nearly 33,000 segments from a 90-min recording, and validate each measurement type against hand-coded annotation. Vowel formant agreement with expert measurements was high (F1 r = 0.89, F2 r = 0.87). Stop VOT showed reliable aggregate means but poor per-token agreement (r = - 0.04) because of a training-deployment mismatch in the neural VOT classifier. Fricative spectral standard deviation agreed strongly with hand-coded values overall (r = 0.80), and center of gravity agreed strongly for sibilants (/s/ r = 0.87, /ʃ/ r = 0.94), while non-sibilant moments diverged systematically. These findings suggest that TAPA can be used to increase access to naturalistic speech data and speed up the processing timeline with experts' supervision.

Acoustic–phonetic analysis

Computational approaches

Speaker diarization

Naturalistic data

Natural language processing

Speech processing

Voice onset time

Spectral moment

UIOWA OA Agreement

Details

Title: Subtitle: Toolkit for acoustic-phonetic analysis of naturalistic speech data
Creators: Ethan Kutlu - University of Iowa
Emerson Peters - University of Washington
Ciara Tapanes - University of Iowa
Sarmad Chandio - University of Iowa
Osama Khalid - University of Iowa
Resource Type: Journal article
Publication Details: Behavior research methods, Vol.58(10), 289
DOI: 10.3758/s13428-026-03174-y
PMID: 42717133
PMCID: PMC13558450
NLM abbreviation: Behav Res Methods
ISSN: 1554-3528
eISSN: 1554-3528
Publisher: Springer Nature
Grant note: University of Iowa's OUR program
EK and EP receive undergraduate research fellowship through the University of Iowa's OUR program. The funds were used to support EP's time in the lab as an undergraduate research assistant.
Language: English
Date published: 09/09/2026
Academic Unit: Communication Sciences and Disorders; Psychological and Brain Sciences; Center for Social Science Innovation
Record Identifier: 9985226072602771

Metrics

2 Record Views