Guardado en:
Detalles Bibliográficos
Autores principales: Swain, Monorama, Maji, Bubai, Mishra, Jagabandhu, Schedl, Markus, Søgaard, Anders, Jensen, Jesper Rindom
Formato: Preprint
Publicado: 2025
Materias:
Acceso en línea:https://arxiv.org/abs/2510.18374
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866917220023533568
author Swain, Monorama
Maji, Bubai
Mishra, Jagabandhu
Schedl, Markus
Søgaard, Anders
Jensen, Jesper Rindom
author_facet Swain, Monorama
Maji, Bubai
Mishra, Jagabandhu
Schedl, Markus
Søgaard, Anders
Jensen, Jesper Rindom
contents In this work, we address the challenge of building fair English ASR systems for second-language speakers. Our analysis of widely used ASR models, Whisper and Seamless-M4T, reveals large fluctuations in word error rate (WER) across 26 accent groups, indicating significant fairness gaps. To mitigate this, we propose fairness-prompted finetuning with lightweight adapters, incorporating Spectral Decoupling (SD), Group Distributionally Robust Optimization (Group-DRO), and Invariant Risk Minimization (IRM). Our proposed fusion of traditional empirical risk minimization (ERM) with cross-entropy and fairness-driven objectives (SD, Group DRO, and IRM) enhances fairness across accent groups while maintaining overall recognition accuracy. In terms of macro-averaged word error rate, our approach achieves a relative improvement of 58.7% and 58.5% over the large pretrained Whisper and SeamlessM4T, and 9.7% and 7.8% over them, finetuning with standard empirical risk minimization with cross-entropy loss.
format Preprint
id arxiv_https___arxiv_org_abs_2510_18374
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Towards Fair ASR For Second Language Speakers Using Fairness Prompted Finetuning
Swain, Monorama
Maji, Bubai
Mishra, Jagabandhu
Schedl, Markus
Søgaard, Anders
Jensen, Jesper Rindom
Computation and Language
In this work, we address the challenge of building fair English ASR systems for second-language speakers. Our analysis of widely used ASR models, Whisper and Seamless-M4T, reveals large fluctuations in word error rate (WER) across 26 accent groups, indicating significant fairness gaps. To mitigate this, we propose fairness-prompted finetuning with lightweight adapters, incorporating Spectral Decoupling (SD), Group Distributionally Robust Optimization (Group-DRO), and Invariant Risk Minimization (IRM). Our proposed fusion of traditional empirical risk minimization (ERM) with cross-entropy and fairness-driven objectives (SD, Group DRO, and IRM) enhances fairness across accent groups while maintaining overall recognition accuracy. In terms of macro-averaged word error rate, our approach achieves a relative improvement of 58.7% and 58.5% over the large pretrained Whisper and SeamlessM4T, and 9.7% and 7.8% over them, finetuning with standard empirical risk minimization with cross-entropy loss.
title Towards Fair ASR For Second Language Speakers Using Fairness Prompted Finetuning
topic Computation and Language
url https://arxiv.org/abs/2510.18374