Work

CPT-Boosted Wav2vec2.0: Towards Noise Robust Speech Recognition for Classroom Environments

Year: 2025

Type: conference-paper

Abstract: Creating Automatic Speech Recognition (ASR) systems that are robust and resilient to classroom conditions is paramount to the development of AI tools to aid teachers and students. In this work, we study the efficacy of continued pretraining (CPT) in adapting Wav2vec2.0 to the classroom domain. We show that CPT is a powerful tool in that regard and reduces the Word Error Rate (WER) of Wav2vec2.0-based models by upwards of 10%. More specifically, CPT improves the model’s robustness to different noises, microphones and classroom conditions.

Source: IEEE International Conference on Acoustics Speech and Signal Processing

DOI: 10.1109/icassp49660.2025.10890830

Authors: Ahmed Adel Attia, Dorottya Demszky, Tolúlọpe Ògúnremí, Jing Liu, Carol Espy-Wilson

Institutions: University of Maryland, College Park, Stanford University

Language: English

Topic: Speech Recognition and Synthesis

Subfield: Artificial Intelligence

Field: Computer Science

Domain: Physical Sciences

SDG: Quality education

Open Access status: green

Funder: Bill and Melinda Gates Foundation