Project Grant 2504020

Award Date 9/1/25
Completion Date 8/31/29
Dollars Obligated $378K
Federal Grant Program
47.070
Assistance Type
Project Grant
Place of Performance
Gettysburg, PA 17325, USA
Similar Awards
This National Science Foundation (NSF) Computer and Information Science and Engineering (CISE) Project Grant award, with a funding amount of $821,902, will support research at Carnegie Mellon University (CMU) to develop a novel artificial intelligence (AI) model called the Phonetic Open Whisper-Style Speech Model (POWSM). The POWSM model is designed to enable speech-to-text transcription for a wide range of language varieties, even when limited digital data is available. The project will...
The National Science Foundation Division of Behavioral and Cognitive Sciences awarded a $239,580 project grant to Gettysburg College on December 1, 2021 with a completion date of May 31, 2025. The grant supports collaborative research to improve techniques of automatic speech recognition and transfer learning using documentary linguistic corpora under the Social, Behavioral, and Economic Sciences program (CFDA 47.075). This program contributes to scientific strength and welfare through promotion...
This Project Grant award from the National Science Foundation's (NSF) Social, Behavioral, and Economic Sciences (CFDA 47.075) program provides $195,040 to Stony Brook University, a prominent research institution, for a 3-year collaborative research project on subregular inference of morpho-phonology. The research aims to advance the understanding of how humans learn language, specifically the mental representations of words and the patterns governing their pronunciation. The project will develop...
This Project Grant award of $448,129 from the National Science Foundation (CFDA 47.084 - NSF Technology, Innovation, and Partnerships) will support the "COLLABORATIVE RESEARCH: REDDDOT PHASE 2: INCLUSIVE AMERICAN LANGUAGE TECHNOLOGIES" project. The goal is to create crucial training datasets, primarily optimized for speech recognition (speech-to-text), for three underrepresented American sociolinguistic contexts: a sociolect, a code-switching language context, and an indigenous...
This Project Grant award from the National Science Foundation's Social, Behavioral, and Economic Sciences (CFDA 47.075) program provides $268,067 to develop advanced speech technologies and create educational resources for language research and learning. The project addresses critical language needs by leveraging automatic speech recognition, text-to-speech, and other speech technologies to bridge the gap between linguistic research and practical application. Key activities include developing...
This Project Grant award from the National Science Foundation's Division of Information and Intelligent Systems (CFDA 47.070 - Computer and Information Science and Engineering) supports research into probing the inner workings of artificial intelligence (AI) systems and comparing them to human cognition during speech recognition. The $50,000 award to the University of Southern California (USC) will fund the development of novel mathematical models and experimental methods to examine how AI...
Northwestern University was awarded a $400,000 Project Grant from the National Science Foundation Social, Behavioral, and Economic Sciences program to develop new methods for analyzing acoustic variation in speech using unsupervised deep learning techniques. The goal is to discover a representational space for speech that captures subtle but meaningful differences in pronunciation in a holistic manner similar to human speech perception abilities. The university will apply these methods to...
This National Science Foundation project grant of $318,850 will fund research at the University of California, Los Angeles from May 2022 to April 2025 under the Computer and Information Science and Engineering program (CFDA 47.070). The research aims to improve speech technology and develop automated oral literacy assessments to better support learning outcomes for young African American English-speaking children. Specifically, the university researchers will develop data augmentation and...
This National Science Foundation project grant of $260,147 will fund research at the University of Washington from May 2022 to April 2025 under the Computer and Information Science and Engineering program (CFDA 47.070). The research aims to improve speech technology and develop automated oral literacy assessment tools for young speakers of African American English to enhance early education outcomes. Specifically, the university researchers will develop data augmentation and normalization...
This $178,992 National Science Foundation project grant supports research at Georgia State University Research Foundation to improve speech technology for better learning outcomes among African American English-speaking children. Funded under the Computer and Information Science and Engineering program, the three-year award aims to develop data augmentation and normalization techniques to increase the amount of training data available and improve automatic speech recognition performance for this...

This Project Grant award of $377,764 from the National Science Foundation (NSF) Computer and Information Science and Engineering (CISE) Federal Grant Program supports research at Gettysburg College to develop a new AI model called POWSM (Phonetic Open Whisper-Style Speech Model) for universal speech-to-text across language varieties.

The project aims to leverage systematic relationships and phonetic foundations to enable speech recognition for low-resource language variants, even when limited digital training data is available. Key objectives include: 1) using POWSM to transcribe pronunciation and enable speech-to-text for previously unsupported language variants by learning similarities and differences between well-resourced and low-resource varieties; 2) constructing synthetic data and language models to decode low-resource variety output from POWSM; and 3) automatically learning phonetic correspondences between language varieties to support basic speech-to-speech translation. The research will be evaluated across major languages including English, Italian, Chinese, German, Arabic, and endangered languages like Nahuatl and Mixtec.

Generated 8/5/25, 5:32 AM