Pitch Accent Detection improves Pretrained Automatic Speech Recognition

David Sasu, Natalie Schluter
8/6/2025
cs.CLcs.SDeess.AS

No confident code implementation found for this paper. 1 possible match can be shown below.

Abstract

We show the performance of Automatic Speech Recognition (ASR) systems that use semi-supervised speech representations can be boosted by a complimentary pitch accent detection module, by introducing a joint ASR and pitch accent detection model. The pitch accent detection component of our model achieves a significant improvement on the state-of-the-art for the task, closing the gap in F1-score by 41%. Additionally, the ASR performance in joint training decreases WER by 28.3% on LibriSpeech, under limited resource fine-tuning. With these results, we show the importance of extending pretrained speech models to retain or re-learn important prosodic cues such as pitch accent.

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. 1 weaker match is hidden by default — verify before relying on them.

No code implementations found yet.

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

Similar Papers

Improving Self-supervised Pre-training using Accent-Specific Codebooks

86% match1 repo192024

Accented Speech Recognition With Accent-specific Codebooks

86% match1 repo192023

Improving Accented Speech Recognition with Multi-Domain Training

84% match2023

Clustering and Mining Accented Speech for Inclusive and Fair Speech Recognition

83% match2024

Improving Accented Speech Recognition using Data Augmentation based on Unsupervised Text-to-Speech Synthesis

82% match2024

Mixture-of-Experts with Intermediate CTC Supervision for Accented Speech Recognition

82% match2026

Cite this paper

@article{sasu2025pitch,
  title  = {Pitch Accent Detection improves Pretrained Automatic Speech Recognition},
  author = {David Sasu and Natalie Schluter},
  year   = {2025},
  eprint = {2508.04814},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2508.04814v1}
}

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/2508.04814.svg)](https://codeofpaper.com/paper/2508.04814)

Discussion