A Parameter-efficient Language Extension Framework for Multilingual ASR
Covering all languages with a multilingual speech recognition model (MASR) is very difficult. Performing language extension on top of an existing MASR is a desirable choice. In this study, the MASR continual learning problem is probabilistically decomposed into language identity prediction (LP) and cross-lingual adaptation (XLA) sub-problems. Based on this, we propose an architecture-based framework for language extension that can fundamentally solve catastrophic forgetting, debudded as PELE. PELE is designed to be parameter-efficient, incrementally incorporating an add-on module to adapt to a new language. Specifically, different parameter-efficient fine-tuning (PEFT) modules and their variants are explored as potential candidates to perform XLA. Experiments are carried out on 5 new languages with a wide range of low-resourced data sizes. The best-performing PEFT candidate can achieve satisfactory performance across all languages and demonstrates superiority in three of five languages over the continual joint learning setting. Notably, PEFT methods focusing on weight parameters or input features are revealed to be limited in performance, showing significantly inferior extension capabilities compared to inserting a lightweight module in between layers such as an Adapter.
Code (0)
등록된 구현이 없습니다.
Tasks
Continual Learningparameter-efficient fine-tuningspeech-recognitionSpeech RecognitionMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
uCLIP: Parameter-Efficient Multilingual Extension of Vision-Language Models with Unpaired Data
Contrastive Language-Image Pre-training (CLIP) has demonstrated strong generalization across a wide range of visual tasks by leveraging large-scale English-image pairs. However, its extension to low-resource languages re…
Learning Language Specific Sub-network for Multilingual Machine Translation
Multilingual neural machine translation aims at learning a single translation model for multiple languages. These jointly trained models often suffer from performance degradation on rich-resource language pairs. We attri…
AttributeMachine TranslationTranslationOFA: A Framework of Initializing Unseen Subword Embeddings for Efficient Large-scale Multilingual Continued Pretraining
Instead of pretraining multilingual language models from scratch, a more efficient method is to adapt existing pretrained language models (PLMs) to new languages via vocabulary extension and continued pretraining. Howeve…
Language ModellingMultilingual Word EmbeddingsWord EmbeddingsFrom English to More Languages: Parameter-Efficient Model Reprogramming for Cross-Lingual Speech Recognition
In this work, we propose a new parameter-efficient learning framework based on neural model reprogramming for cross-lingual speech recognition, which can \textbf{re-purpose} well-trained English automatic speech recognit…
Automatic Speech RecognitionAutomatic Speech Recognition (ASR)speech-recognitionSpeech RecognitionA Multi-Pairwise Extension of Procrustes Analysis for Multilingual Word Translation
In this paper we present a novel approach to simultaneously representing multiple languages in a common space. Procrustes Analysis (PA) is commonly used to find the optimal orthogonal word mapping in the bilingual case. …
TranslationWord Translation