top of page

Tools

Below are several of my favorite research tools and teaching resources related to

Acoustics / Phonetics / Speech Science

I've also included resources on programming, including tools for programming perceptual and behavioral experiments

SpeechBox

SpeechBox (formerly known as OSCAAR) is a web-based system for managing and providing access to a large set of digital speech corpora. SpeechBox houses approximately 90,000 audio speech files from many different talkers, in many different languages, and from many different speech elicitation materials within dozens of different digital speech corpora.

speechbox.png

R for Data Science

R for Data Science teaches you how to do data science with R: You’ll learn how to get your data into R, get it into the most useful structure, transform it, visualize it and model it. This book offers a practicum of skills for data science. You’ll learn how to use the grammar of graphics, literate programming, and reproducible research to save time. You’ll also learn how to manage cognitive resources to facilitate discoveries when wrangling, visualizing, and exploring data.

cover.png

Sage Research Methods

Sage Research Methods is the ultimate methods library with more than 1000 books, reference works, journal articles, and instructional videos by world-leading academics from across the social sciences. The site is designed to guide users to the content they need to learn a little or a lot about their method. The Methods Map can help those less familiar with research methods to find the best technique to use in their research.

sage_research.jpg

Twitter for Scientists

" I believe that Twitter can provide extraordinary opportunities for scientists, regardless of their seniority, mentors, or institution. By actively contributing to Twitter, I’ve kept up-to-date with emerging methods, several doors have opened for research collaborations, and I’ve been introduced to a supportive community of like-minded scientists. Most important, I’ve received valuable feedback on my work and been able to share my research to people that would have not otherwise seen it. In fact, if it wasn’t for Twitter I don’t think I’d still be in academia." - Daniel Quintana 

book_cover.png

Gramle

Dallin Tucker & Benjamin V. Tucker of the Northern Arizona Speech Communication Laboratory created an excellent tool for new and experienced phoneticians to get practice interpreting spectrograms. All the words in Gramle are English words produced by a male speaker of English from the MALD dataset. Transcriptions are phonemic and are based on a general American English dialect based on the CMU-dictionary transcriptions. If you were obsessed with WORDLE and are interested in a bit of a challenge, check out Gramle!

Screenshot 2023-05-27 at 10.28.36 PM.png

Corpus Phonetics Tutorial
from Eleanor Chodroff

In addition to other fantastic resources on R and understanding/presenting linguistic data, Eleanor Chodroff provides an in depth tutorial on how to approach and conduct analyses of speech corpora. She covers basic tools and resources required for these analyses.

Sound Waves

Automated Phonetic Transcription Comparison Tool (APTct)

The Automated Phonetic Transcription (APT) Comparison Tool (APTct) is an online tool that facilitates the comparison of phonetic transcriptions for a variety of clinical and research purposes. It uses an IPA graphical keyboard for straight forward transcription input, and a custom edit distance algorithm designed to align transcriptions in an intuitive way and then calculate differences quantitatively. This allows for objective scoring of transcriptions of even severely impaired productions, which may be difficult to score via traditional comparison methods.

Screenshot 2023-06-01 at 9.07.59 AM.png

NCSU Phonetics Lab Script Repository

Don't have the time (or patience... ) to learn how to write Praat scripts from scratch? The NCSU Phonetics Lab has a great repository of scripts for Praat and other programming languages... You can also find numerous teaching/lecture resources on their lab site!

Screenshot 2023-06-01 at 9.22.11 AM.png

Dynamic Time Warping Tutorial

Romain Tavenard's blog post on dynamic time warping provides on overview of the technique as well as examples of analyses comparing alignment based metrics.

Screenshot 2023-06-01 at 9.44.29 AM.png

DARLA: Dartmouth Linguistic Automation

DARLA is a web application providing two main functionalities for vowel extraction from speech: completely automated and semi-automated. The completely automated system transcribes the input speech data using automatic speech recognition (ASR), and then runs it through forced alignment and formant extraction. The semi-automated system is a forced-alignment approach that aligns and extracts vowel formants from speech with manual transcriptions.

D-Pine_CMYK.jpg
bottom of page