Saved in:
Bibliographic Details
Main Authors: Xu, Jing, Wu, Minglin, Chen, Xueyuan, Wu, Xixin, Meng, Helen
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2602.12746
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866918335986270208
author Xu, Jing
Wu, Minglin
Chen, Xueyuan
Wu, Xixin
Meng, Helen
author_facet Xu, Jing
Wu, Minglin
Chen, Xueyuan
Wu, Xixin
Meng, Helen
contents Despite their impressive performance, self-supervised speech models often struggle to generalize to new languages and tend to forget previously acquired knowledge during continual training. To address this, we propose Lamer-SSL, a parameter-efficient framework that integrates a Layer-Aware MixturE of LoRA Experts (Lamer) module with a replay strategy. The Lamer module enables flexible balancing between shared and language-specific representations, while layer-aware expert allocation assigns more experts to deeper layers where semantic information is richer. Meanwhile, the replay strategy retains prior knowledge using minimal data, mitigating forgetting during continual training. Experiments on automatic speech recognition (ASR) and language identification (LID) demonstrate that Lamer-SSL extends self-supervised models to new languages effectively while maintaining strong performance on previously learned languages with only 2.14% parameters being trainable.
format Preprint
id arxiv_https___arxiv_org_abs_2602_12746
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Lamer-SSL: Layer-aware Mixture of LoRA Experts for Continual Multilingual Expansion of Self-supervised Models without Forgetting
Xu, Jing
Wu, Minglin
Chen, Xueyuan
Wu, Xixin
Meng, Helen
Computation and Language
Audio and Speech Processing
Despite their impressive performance, self-supervised speech models often struggle to generalize to new languages and tend to forget previously acquired knowledge during continual training. To address this, we propose Lamer-SSL, a parameter-efficient framework that integrates a Layer-Aware MixturE of LoRA Experts (Lamer) module with a replay strategy. The Lamer module enables flexible balancing between shared and language-specific representations, while layer-aware expert allocation assigns more experts to deeper layers where semantic information is richer. Meanwhile, the replay strategy retains prior knowledge using minimal data, mitigating forgetting during continual training. Experiments on automatic speech recognition (ASR) and language identification (LID) demonstrate that Lamer-SSL extends self-supervised models to new languages effectively while maintaining strong performance on previously learned languages with only 2.14% parameters being trainable.
title Lamer-SSL: Layer-aware Mixture of LoRA Experts for Continual Multilingual Expansion of Self-supervised Models without Forgetting
topic Computation and Language
Audio and Speech Processing
url https://arxiv.org/abs/2602.12746