Papers › Lightweight Adapter Tuning for Multilingual Speech Translation

Lightweight Adapter Tuning for Multilingual Speech Translation

2 Jun 2021ACL 2021 5arXiv:2106.01463archive 2025-07-28

Hang Le, Juan Pino, Changhan Wang, Jiatao Gu, Didier Schwab, Laurent Besacier

Adapter modules were recently introduced as an efficient alternative to fine-tuning in NLP. Adapter tuning consists in freezing pretrained parameters of a model and injecting lightweight modules between layers, resulting in the addition of only a small number of task-specific trainable parameters. While adapter tuning was investigated for multilingual neural machine translation, this paper proposes a comprehensive analysis of adapters for multilingual speech translation (ST). Starting from different pre-trained models (a multilingual ST trained on parallel data or a multilingual BART (mBART) trained on non-parallel multilingual data), we show that adapters can be used to: (a) efficiently specialize ST to specific language pairs with a low extra cost in terms of parameters, and (b) transfer from an automatic speech recognition (ASR) task and an mBART pre-trained model to a multilingual ST task. Experiments show that adapter tuning offer competitive results to full fine-tuning, while being much more parameter-efficient.

PaperPDFConference PDFCode

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

formiel/fairseq officialmentioned in paperpytorchMIT report
formiel/fairseq officialpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Automatic Speech RecognitionAutomatic Speech Recognition (ASR)Machine TranslationSpeech RecognitionSpeech-to-Text TranslationTranslationspeech-recognition

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Speech-to-Text Translation MuST-C Transformer with Adapters SacreBLEU 26.61 #1 of 2 Archive leaderboard report
Speech-to-Text Translation MuST-C EN->DE Transformer with Adapters Case-sensitive sacreBLEU 24.63 #4 of 8 Archive leaderboard report
Speech-to-Text Translation MuST-C EN->ES Transformer with Adapters Case-sensitive sacreBLEU 28.73 #1 of 5 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

AdamAdapterAttentionBARTBPEDense ConnectionsDropoutLayer NormalizationLinear LayerMulti-Head AttentionResidual ConnectionSoftmaxmBART

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections