Publications
2025
-
Leveraging ASR and LLMs for Automated Scoring and Feedback in Children’s Spoken Language AssessmentsIn Proc. 10th Workshop on Speech and Language Technology in Education (SLaTE) 2025
-
An Age-Agnostic System for Robust Speaker VerificationIn Proc. 7th Workshop on Child Computer Interaction (WOCCI 2025) 2025
-
Benchmarking Training Paradigms, Dataset Composition, and Model Scaling for Child ASR in ESPnetIn Proc. 7th Workshop on Child Computer Interaction (WOCCI 2025) 2025
-
CHSER: A Dataset and Case Study on Generative Speech Error Correction for Child ASRProc. INTERSPEECH 2025 2025
-
Addressing Bias in Spoken Language Systems Used in the Development and Implementation of Automated Child Language-Based AssessmentJournal of Educational Measurement 2025
-
Selective Attention Merging for Low Resource Tasks: A Case Study of Child ASRICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) 2025
2024
-
The JIBO Kids Corpus: A speech dataset of child-robot interactions in a classroom environmentJASA Express Letters Nov 2024
-
Benchmarking Children’s ASR with Supervised and Self-supervised Speech Foundation ModelsProc. INTERSPEECH 2024 Nov 2024
-
Large Language Model-based Pipeline for Item Difficulty and Response Time Estimation for Educational AssessmentsNAACL 2024 Workshops - Proceedings of the Nineteenth Workshop on Innovative Use of NLP for Building Educational Applications (BEA) Nov 2024
-
SOA: Reducing Domain Mismatch in SSL Pipeline by Speech Only Adaptation for Low Resource ASR2024 IEEE International Conference on Acoustics, Speech, and Signal Processing Workshops (ICASSPW) Nov 2024
-
An exploratory study on dialect density estimation for children and adult’s African American EnglishThe Journal of the Acoustical Society of America Nov 2024
-
CORAAL QA: A Dataset and Framework for Open Domain Spontaneous Speech Question Answering from Long Audio FilesIn ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) Nov 2024
-
UniEnc-CASSNAT: An Encoder-Only Non-Autoregressive ASR for Speech SSL ModelsIEEE Signal Processing Letters Nov 2024
2023
-
An Analysis of Large Language Models for African American English Speaking Children’s Oral Language AssessmentJournal of Black Excellence in Engineering, Science, & Technology Nov 2023
-
An Equitable Framework for Automatically Assessing Children’s Oral Narrative Language AbilitiesIn Proc. INTERSPEECH 2023 Nov 2023
-
Towards Automatically Assessing Children’s Oral Picture Description TasksIn Proc. 9th Workshop on Speech and Language Technology in Education (SLaTE) Nov 2023
2020
-
A hybrid feature preservation technique based on luminosity and edge based contrast enhancement in color fundus imagesBiocybernetics and Biomedical Engineering Nov 2020