Saved in:
Bibliographic Details
Main Authors: Madden, Jordan, Stone, Matthew, Johnson, Dimitri, Geddez, Daniel
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2507.16834
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916858120110080
author Madden, Jordan
Stone, Matthew
Johnson, Dimitri
Geddez, Daniel
author_facet Madden, Jordan
Stone, Matthew
Johnson, Dimitri
Geddez, Daniel
contents Although Jamaican Patois is a widely spoken language, current speech recognition systems perform poorly on Patois music, producing inaccurate captions that limit accessibility and hinder downstream applications. In this work, we take a data-centric approach to this problem by curating more than 40 hours of manually transcribed Patois music. We use this dataset to fine-tune state-of-the-art automatic speech recognition (ASR) models, and use the results to develop scaling laws for the performance of Whisper models on Jamaican Patois audio. We hope that this work will have a positive impact on the accessibility of Jamaican Patois music and the future of Jamaican Patois language modeling.
format Preprint
id arxiv_https___arxiv_org_abs_2507_16834
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Towards Robust Speech Recognition for Jamaican Patois Music Transcription
Madden, Jordan
Stone, Matthew
Johnson, Dimitri
Geddez, Daniel
Audio and Speech Processing
Artificial Intelligence
Computation and Language
Although Jamaican Patois is a widely spoken language, current speech recognition systems perform poorly on Patois music, producing inaccurate captions that limit accessibility and hinder downstream applications. In this work, we take a data-centric approach to this problem by curating more than 40 hours of manually transcribed Patois music. We use this dataset to fine-tune state-of-the-art automatic speech recognition (ASR) models, and use the results to develop scaling laws for the performance of Whisper models on Jamaican Patois audio. We hope that this work will have a positive impact on the accessibility of Jamaican Patois music and the future of Jamaican Patois language modeling.
title Towards Robust Speech Recognition for Jamaican Patois Music Transcription
topic Audio and Speech Processing
Artificial Intelligence
Computation and Language
url https://arxiv.org/abs/2507.16834