{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/exploiting-adapters-for-cross-lingual-low","title":"Exploiting Adapters for Cross-lingual Low-resource Speech Recognition","arxiv_id":"2105.11905","date":"2021-05-18","proceeding":null,"authors":["Wenxin Hou","Han Zhu","Yidong Wang","Jindong Wang","Tao Qin","Renjun Xu","Takahiro Shinozaki"],"abstract":"Cross-lingual speech adaptation aims to solve the problem of leveraging multiple rich-resource languages to build models for a low-resource target language. Since the low-resource language has limited training data, speech recognition models can easily overfit. In this paper, we propose to use adapters to investigate the performance of multiple adapters for parameter-efficient cross-lingual speech adaptation. Based on our previous MetaAdapter that implicitly leverages adapters, we propose a novel algorithms called SimAdapter for explicitly learning knowledge from adapters. Our algorithm leverages adapters which can be easily integrated into the Transformer structure.MetaAdapter leverages meta-learning to transfer the general knowledge from training data to the test language. SimAdapter aims to learn the similarities between the source and target languages during fine-tuning using the adapters. We conduct extensive experiments on five-low-resource languages in Common Voice dataset. Results demonstrate that our MetaAdapter and SimAdapter methods can reduce WER by 2.98% and 2.55% with only 2.5% and 15.5% of trainable parameters compared to the strong full-model fine-tuning baseline. Moreover, we also show that these two novel algorithms can be integrated for better performance with up to 3.55% relative WER reduction.","url_abs":"https://arxiv.org/abs/2105.11905v2","url_pdf":"https://arxiv.org/pdf/2105.11905v2.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"exploiting-adapters-for-cross-lingual-low","repo_url":"https://github.com/jindongwang/transferlearning","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"exploiting-adapters-for-cross-lingual-low","repo_url":"https://github.com/jindongwang/transferlearning/tree/master/code/ASR","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"cross-lingual-asr","task_name":"Cross-Lingual ASR"},{"task_slug":"general-knowledge","task_name":"General Knowledge"},{"task_slug":"meta-learning","task_name":"Meta-Learning"},{"task_slug":"speech-recognition","task_name":"Speech Recognition"},{"task_slug":"speech-recognition-1","task_name":"speech-recognition"}],"methods":[{"method_slug":"absolute-position-encodings","method_name":"Absolute Position Encodings"},{"method_slug":"adam","method_name":"Adam"},{"method_slug":"attention","method_name":"Attention"},{"method_slug":"bpe","method_name":"BPE"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"label-smoothing","method_name":"Label Smoothing"},{"method_slug":"layer-normalization","method_name":"Layer Normalization"},{"method_slug":"linear-layer","method_name":"Linear Layer"},{"method_slug":"multi-head-attention","method_name":"Multi-Head Attention"},{"method_slug":"position-wise-feed-forward-layer","method_name":"Position-Wise Feed-Forward Layer"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"simadapter","method_name":"SimAdapter"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"transformer","method_name":"Transformer"}],"datasets_introduced":[],"methods_introduced":[{"slug":"simadapter","name":"SimAdapter","full_name":"SimAdapter"}],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2105.11905","atlas_url":"https://app.syntology.ai/?focus=2105.11905","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}