iSpraak: A web-based application for second language pronunciation instruction, assessment, and research

FAIN: HAA-284849-22

St. Louis University (St. Louis, MO 63103-2097)
Daniel Nickolai (Project Director: June 2021 to present)
Kathleen Llewellyn (Co Project Director: January 2022 to present)
Sarah Bauer (Co Project Director: January 2022 to present)
Christina Garcia (Co Project Director: January 2022 to present)
Amy E. Wright (Co Project Director: January 2022 to present)

Scaling up development and dissemination of the iSpraak application as a free and open source language pronunciation instruction and learning tool. 

This NEH Digital Humanities Advancement Grant proposal outlines the plan to enhance, scale, and provide free access to the web application iSpraak. This digital platform equips educators and scholars with an innovative tool for second language pronunciation instruction, assessment, and research. Originally developed for internal use at Saint Louis University in 2014, iSpraak has now been used by tens of thousands of students and instructors across the globe. NEH funding is currently sought in order to continue development, remove cost barriers to access, and to make the platform fully open and accessible to all interested parties.

Associated Products

iSpraak (Computer Program)
Title: iSpraak
Author: Dan Nickolai
Abstract: iSpraak is a free and open source online activity generator designed for second language educators. Dr. Dan Nickolai of Saint Louis University developed iSpraak to automate speech evaluation of language learners and to provide them with instantaneous corrective feedback. The National Endowment for the Humanities and the SLU Research Institute have provided funding for its development and open access.
Year: 2014
Primary URL: https://www.ispraak.net
Primary URL Description: This is the main page of the iSpraak platform.
Access Model: Open Access
Programming Language/Platform: PHP, Javascript
Source Available?: Yes

Quantifying ASR Pronunciation Gains with Large Learner Datasets (Conference Paper/Presentation)
Title: Quantifying ASR Pronunciation Gains with Large Learner Datasets
Author: Dan Nickolai
Abstract: CALL tools have become increasingly dependent on Automatic Speech Recognition (ASR) to provide learner feedback for L2 pronunciation. Studies to date on ASR have largely been conducted by research practitioners with small-to-medium sized subject populations at single institutions. The present study differs in that it examines a sizable 8-year dataset from iSpraak, an open source pronunciation tool. Quantitative analysis of anonymized learner interactions with this platform reveal significant gains in intelligibility measures across multiple languages. Results also suggest that the extent of ASR’s ability to improve learner pronunciation may be L2 dependent.
Date: 05/23/2024
Primary URL: https://calico.org/2024-sessions/
Conference Name: CALICO (Computer Assisted Language Instruction Consortium)

Cornell University's LRC Speaker Series (Public Lecture or Presentation)
Title: Cornell University's LRC Speaker Series
Abstract: This presentation showcased the latest feature developments to the iSpraak platform. This free online tool incorporates multilingual Automatic Speech Recognition and Text-to-Speech technologies to both model and assess pronunciation in 36 different languages. Now generously funded by the National Endowment for the Humanities, iSpraak has significantly expanded on its previous feature set and has adopted new tools for learners, teachers, and researchers.
Author: Dan Nickolai
Date: 04/16/2024
Location: Cornell University
Primary URL: https://events.cornell.edu/event/lrc_speakerseries_DanNickolai
Primary URL Description: Event information on Cornell's website
Secondary URL: https://www.youtube.com/watch?v=-YR6DhW2Yac
Secondary URL Description: Video recording of presentation

Speaking of Language Podcast (Radio/Audio Broadcast or Recording)
Title: Speaking of Language Podcast
Director: Angelika Kraemer
Producer: Angelika Kraemer
Abstract: Dr. Dan Nickolai, current IALLT president and director of the Language Resource Center at St. Louis University, introduces iSpraak, a web-based tool for practice and assessment of second language pronunciation.
Date: 04/24/2024
Primary URL: https://www.podbean.com/media/share/pb-b7pnu-15f30a7?utm_campaign=embed_player_share&utm_medium=dlink&utm_source=embed_player
Primary URL Description: This is the episode of "Speaking of Language" on the PodBean website.
Format: Web

Aggregating the evidence of automatic speech recognition research claims in CALL (Article)
Title: Aggregating the evidence of automatic speech recognition research claims in CALL
Author: Dan Nickolai
Author: Emma Schaefer
Author: aula Figueroa
Abstract: This review provides an overview and analysis of ASR (automatic speech recognition) research claims identified in CALL (computer-assisted language learning) studies from the past decade. When taken separately, few conclusions can be drawn and little extrapolation is possible from any one isolated investigation. Empirical studies on ASR vary tremendously in size, scope, and research questions posited. However, clear patterns and implications for educators and CALL researchers are beginning to emerge from the data. This research synthesis of 50 studies considers how effective ASR tools are at assessing and ultimately improving L2 pronunciation. Two novel rubrics are proposed to categorize evidence strength for individual studies and to further classify the frequency of claims across multiple studies. Results from this analysis suggest that there are strong empirical arguments in favor of utilizing ASR for pronunciation instruction and evaluation. Specifically, ASR has a demonstrated capacity to accurately identify errors, improve pronunciation, and is strongly associated with a positive student experience.
Year: 2024
Primary URL: https://doi.org/10.1016/j.system.2024.103250
Primary URL Description: DOI link for article
Format: Journal
Periodical Title: System
Publisher: Elsevier

iSpraak: A free pronunciation platform (Public Lecture or Presentation)
Title: iSpraak: A free pronunciation platform
Abstract: iSpraak is a free and open source online pronunciation platform designed for second language educators. This tool empowers learners to work on their pronunciation in 36 different languages by coupling rich audio models with real-time corrective feedback. This webinar will present a tour of the platform and offer some guidance for attendees wanting to create their own speech activities. This project is funded by the National Endowment for the Humanities and the SLU Research Institute.
Author: Dan Nickolai
Date: 08/10/2023
Location: Online
Primary URL: https://iallt.org/webinars/free-webinar-for-august-10-2023/
Primary URL Description: Announcement of Webinar (Original broadcast was open to public; archived recordings available to IALLT members)

Modeling and Evaluating L2 Speech with iSpraak (Conference Paper/Presentation)
Title: Modeling and Evaluating L2 Speech with iSpraak
Author: Dan Nickolai
Abstract: This presentation will showcase the latest feature developments to the iSpraak platform. This free online tool incorporates multilingual Automatic Speech Recognition and Text-to-Speech technologies to both model and assess pronunciation in 36 different languages. Now generously funded by the National Endowment for the Humanities, iSpraak has significantly expanded on its previous feature set and has adopted new tools for learners, teachers, and researchers. This presentation will include information and guidelines on using the platform, and the developer will be on site to answer questions and to provide opportunities to access and interact with the program.
Date: 06/15/2023
Primary URL: https://iallt.org/iallt-2023/
Primary URL Description: Conference Website Schedule
Conference Name: IALLT 2023 (New Orleans, Louisiana)

iSpraak – Automatic Speech Recognition for Everyone (Conference Paper/Presentation)
Title: iSpraak – Automatic Speech Recognition for Everyone
Author: Dan Nickolai
Author: Lillian Jones
Abstract: iSpraak is a pronunciation activity platform designed for foreign language educators. This online tool is meant to serve as a supplemental resource for instructors seeking to incorporate automated and individualized pronunciation feedback into their courses. Now generously funded by the National Endowment for the Humanities, iSpraak has expanded on its previous feature set and is available at no cost to users. The developer will be on site to answer questions and provide conference attendees a chance to interact with the program.
Date: 06/08/2023
Primary URL: https://calico.org/2023-conference-workshops/
Primary URL Description: CALICO 2023 Schedule of Presentations
Conference Name: CALICO

Quantifying the impact of ASR-based instruction: What does the iSpraak platform learner data show? (Article)
Title: Quantifying the impact of ASR-based instruction: What does the iSpraak platform learner data show?
Author: Dan Nickolai
Abstract: Computer-assisted Pronunciation Training (CAPT) tools have become increasingly dependent on Automatic Speech Recognition (ASR) technology to provide automated corrective pronunciation feedback to learners. The extent to which ASR-based tools measurably improve second language (L2) pronunciation is of great interest to language educators globally, and Computer-assisted Language Learning (CALL) researchers. Studies to date have largely been conducted by research practitioners with small-to-medium sized samples at single institutions. The findings and conclusions drawn from such small-scale data collection might be significantly bolstered by analysing the vast stores of learner data from large CAPT platforms. This study is informed by a sizable eight-year dataset from iSpraak, an open-source pronunciation tool designed to model and evaluate L2 speech. Quantitative analysis of anonymised learner interactions with this application reveals significant gains in intelligibility measures across multiple languages. Results also suggest that the extent of ASR’s ability to improve learner pronunciation may be L2 dependent.
Year: 2024
Primary URL: https://doi.org/10.4995/eurocall.2024.20221
Access Model: Open Access
Format: Journal
Publisher: The EuroCALL Review

---