AsyncSwitch: Asynchronous Text-Speech Adaptation for Code-Switched ASR

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Nguyen, Tuan, Tran, Huy-Dat
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915348253507584
author Nguyen, Tuan
Tran, Huy-Dat
author_facet Nguyen, Tuan
Tran, Huy-Dat
contents Developing code-switched ASR systems is challenging due to language ambiguity and limited exposure to multilingual, code-switched data, while collecting such speech is costly. Prior work generates synthetic audio from text, but these methods are computationally intensive and hard to scale. We introduce AsyncSwitch, a novel asynchronous adaptation framework that leverages large-scale, text-rich web data to pre-expose ASR models to diverse code-switched domains before fine-tuning on paired speech-text corpora. Our three-stage process (1) trains decoder self-attention and feedforward layers on code-switched text, (2) aligns decoder and encoder via cross-attention using limited speech-text data, and (3) fully fine-tunes the entire model. Experiments with Whisper on Malay-English code-switching demonstrate a 9.02% relative WER reduction, while improving monolingual performance in Singlish, Malay, and other English variants.
format Preprint
id arxiv_https___arxiv_org_abs_2506_14190
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle AsyncSwitch: Asynchronous Text-Speech Adaptation for Code-Switched ASR
Nguyen, Tuan
Tran, Huy-Dat
Computation and Language
Sound
Audio and Speech Processing
Developing code-switched ASR systems is challenging due to language ambiguity and limited exposure to multilingual, code-switched data, while collecting such speech is costly. Prior work generates synthetic audio from text, but these methods are computationally intensive and hard to scale. We introduce AsyncSwitch, a novel asynchronous adaptation framework that leverages large-scale, text-rich web data to pre-expose ASR models to diverse code-switched domains before fine-tuning on paired speech-text corpora. Our three-stage process (1) trains decoder self-attention and feedforward layers on code-switched text, (2) aligns decoder and encoder via cross-attention using limited speech-text data, and (3) fully fine-tunes the entire model. Experiments with Whisper on Malay-English code-switching demonstrate a 9.02% relative WER reduction, while improving monolingual performance in Singlish, Malay, and other English variants.
title AsyncSwitch: Asynchronous Text-Speech Adaptation for Code-Switched ASR
topic Computation and Language
Sound
Audio and Speech Processing
url https://arxiv.org/abs/2506.14190