Continued Pretraining for Domain Adaptation of Wav2vec2.0 in Automatic Speech Recognition for Elementary Math Classroom Settings

Ahmed Adel Attia, Dorottya Demszky, Tolulope Ogunremi, Jing Liu, Carol Espy-Wilson
5/15/2024
cs.CLcs.AIeess.AS

No confident code implementation found for this 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, classroom conditions as well as classroom demographics. Our CPT models show improved ability to generalize to different demographics unseen in the labeled finetuning data.

View on arXivView PDF

Code Implementations

No confident code match yet

We couldn't find an author-owned or strongly-evidenced community implementation for this paper. Any repos shown below are weak matches — verify before relying on them.

No code implementations found yet.

Know of an implementation? Let us know in the comments below!

Similar Papers

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

97% match2024

From Weak Labels to Strong Results: Utilizing 5,000 Hours of Noisy Classroom Transcripts with Minimal Accurate Data

82% match2025

FusDom: Combining In-Domain and Out-of-Domain Knowledge for Continuous Self-Supervised Learning

81% match1 repo32023

Improving Low-Resource Speech Recognition with Pretrained Speech Models: Continued Pretraining vs. Semi-Supervised Training

81% match2022

SimClass: A Classroom Speech Dataset Generated via Game Engine Simulation For Automatic Speech Recognition Research

80% match2025

Improving noisy student training for low-resource languages in End-to-End ASR using CycleGAN and inter-domain losses

80% match2024

Cite this paper

@article{attia2024continued,
  title  = {Continued Pretraining for Domain Adaptation of Wav2vec2.0 in Automatic Speech Recognition for Elementary Math Classroom Settings},
  author = {Ahmed Adel Attia and Dorottya Demszky and Tolulope Ogunremi and Jing Liu and Carol Espy-Wilson},
  year   = {2024},
  eprint = {2405.13018},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2405.13018v1}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2405.13018.svg)](https://codeofpaper.com/paper/2405.13018)

Discussion