Master-asr: Achieving Multilingual Scalability And Low-resource Adaptation In ASR With Modular Learning
2023 · Zhongzhi Yu, Yang Zhang, Kaizhi Qian, et al.
Abstract
Despite the impressive performance recently achieved by automatic speech recognition (ASR), we observe two primary challenges that hinder its broader applications: (1) The difficulty of introducing scalability into the model to support more languages with limited training, inference, and storage overhead; (2) The low-resource adaptation ability that enables effective low-resource adaptation while avoiding over-fitting and catastrophic forgetting issues. Inspired by recent findings, we hypothesize that we can address the above challenges with modules widely shared across languages. To this end, we propose an ASR framework, dubbed \METHODNS, that, \textit\{for the first time\}, simultaneously achieves strong multilingual scalability and low-resource adaptation ability thanks to its modularize-then-assemble strategy. Specifically, \METHOD learns a small set of generalizable sub-modules and adaptively assembles them for different languages to reduce the multilingual overhead and enable eff
Authors
(none)
Tags
Stats
Related papers
- Adaptive Activation Network For Low Resource Multilingual Speech Recognition (2022)0.00
- Towards One Model To Rule All: Multilingual Strategy For Dialectal Code-switching Arabic ASR (2021)9.03
- MOSA: Mixtures Of Simple Adapters Outperform Monolithic Approaches In Llm-based Multilingual ASR (2025)0.00
- SSHR: Leveraging Self-supervised Hierarchical Representations For Multilingual Automatic Speech Recognition (2023)0.00
- Building Robust And Scalable Multilingual ASR For Indian Languages (2025)0.00
- Multilingual Sequence-to-sequence Speech Recognition: Architecture, Transfer Learning, And Language Modeling (2018)13.84
- Parameter-efficient Adaptation Of Multilingual Multimodal Models For Low-resource ASR (2024)2.26
- MSA-ASR: Efficient Multilingual Speaker Attribution With Frozen ASR Models (2024)2.26