Project Grant FA23862314098

This Project Grant award of $563,693, provided by the National Science Foundation (NSF) under the Computer and Information Science and Engineering (CFDA 47.070) program, aims to advance voice conversion models and technologies. The key research areas include: Exploring self-supervised learning of speaker identity and emotion representations to enable robust voice conversion that can faithfully represent individual speech characteristics and emotional states. Investigating voice conversion...

The National Science Foundation Division of Information and Intelligent Systems awarded a $400,000 Project Grant to The Regents of the University of California for collaborative research titled "Flexible Deep Speech Synthesis through Gestural Modeling." The three-year award runs from October 1, 2021 through September 30, 2024. The research aims to advance development of flexible deep speech synthesis through gestural modeling, in alignment with the goals of the Computer and Information...

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 Project Grant award from the National Science Foundation (NSF) Division of Behavioral and Cognitive Sciences supports research at the University of California, Irvine (UC Irvine) to investigate the neural mechanisms underlying speech production. The project aims to generate a functional map of the brain systems that enable fluent speech, with the goal of improving diagnosis and treatment of speech production deficits. The $965,471 award, effective August 1, 2023 through July 31, 2026,...

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 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...

This $200,000 Project Grant award from the National Science Foundation's (NSF) Social, Behavioral, and Economic Sciences (CFDA 47.075) program supports research into how emotions are encoded in the brain during narrative listening. The project aims to investigate the representations of affect (valence and arousal) across brain regions and frequencies using functional magnetic resonance imaging (fMRI) and electroencephalography (EEG) data collected from a large, diverse sample of adults aged...

The National Institute on Deafness and Other Communication Disorders (NIDCD) awarded a $947,128 Project Grant (CFDA 93.173) to Emory University to conduct research on optimizing voice therapy for individuals with voice disorders. The key objectives are to compare outcomes between non-hierarchical and hierarchical delivery methods of conversation training therapy (CTT), and to investigate the effects of the clear speech component on voice quality and outcomes. This research aims to enhance...

This Project Grant award from the National Science Foundation's (NSF) Computer and Information Science and Engineering (CISE) program, CFDA 47.070, will develop adaptive artificial intelligence systems to provide accessible audio captioning of non-speech sounds in digital media content. The $237,141 award to New York University aims to ensure that all citizens can fully participate in digital education, entertainment, and civic life by creating tools to make non-speech audio cues, such as...

This $430,375 Project Grant award from the National Institute on Deafness and Other Communication Disorders (NIDCD), part of the Research Related to Deafness and Communication Disorders (CFDA 93.173) federal grant program, aims to validate the use of artificial intelligence (AI) techniques applied to video and speech data for objectively evaluating social interaction and mental health in individuals with mild cognitive impairment (MCI). The project will be carried out by Emory University, a...