Methods › Audio › Speech Recognition › XLSR
XLSR
archive 2025-07-28 Description, source and code snippet are the archive's method entry.
XLSR is a multilingual speech recognition model built on wav2vec 2.0 which is trained by solving a contrastive task over masked latent speech representations and jointly learns a quantization of the latents shared across languages. The model is fine-tuned on labeled data and experiments show that cross-lingual pretraining significantly outperforms monolingual pretraining. A shared quantization module over feature encoder representations produces multilingual quantized speech units whose embeddings are then used as targets for a Transformer trained by contrastive learning. The model learns to share discrete tokens across languages, creating bridges across languages.
In Syntology name not resolved (unknown_name). The lookup matched no method, paper or venue by this name; that asserts nothing about whether code exists.
Syntology's have check for this name (free, it answers coverage only), read 2026-10-05; ask it again live. A level is the served verification level of that one answer; nothing here is summed across methods.
Papers archive 2025-07-28
archive papers tagged: 20 · with a code link: 4 · where Syntology ran a sample: 1 (1 with a run with no instrument failure, 0 where every run was a failure of Syntology's instrument) Syntology
Show: all tagged papersonly where code ran (1 of 20 tagged: 1 with a run with no instrument failure, 0 where every run was a failure of Syntology's instrument)
Page 1 of 1: papers 1 to 20 of 20, newest first by the archive's date (ties by slug), in archive order.
Repository counts are the archive's code-links table. A Syntology line states what Syntology ran from that paper's harvested code, as “N ran (of which C constructed an object rather than computing a result; K with no instrument failure: H honoured, V violated, P with no contract checked; I where Syntology's instrument failed) · U unverified”; the instrument figure counts failures of Syntology's instrument, not of the code. It is per sample and not a correctness claim. When the archive marks a repository official for the paper, the line starts with that repository's state (the archive's flag, not a verdict on who wrote the code; “community repositories only” when every sample that ran came from a community repository, “official: no sample here; runs from other or unrecorded repositories” when some came from a repository the paper names or has in its text, or from none recorded); hover it for the repositories the samples that ran came from.
-
EMO-Debias: Benchmarking Gender Debiasing Techniques in Multi-Label Speech Emotion Recognition 5 Jun 2025 · 0 repositories · arXiv:2506.04652
-
Self-supervised ASR Models and Features For Dysarthric and Elderly Speech Recognition 3 Jul 2024 · 0 repositories · arXiv:2407.13782
-
Less Forgetting for Better Generalization: Exploring Continual-learning Fine-tuning Methods for Speech Self-supervised Representations 30 Jun 2024 · 0 repositories · arXiv:2407.00756
-
Transcription and translation of videos using fine-tuned XLSR Wav2Vec2 on custom dataset and mBART 1 Mar 2024 · 0 repositories · arXiv:2403.00212
-
End to end Hindi to English speech conversion using Bark, mBART and a finetuned XLSR Wav2Vec2 11 Jan 2024 · 0 repositories · arXiv:2401.06183
-
Self-supervised Adaptive Pre-training of Multilingual Speech Models for Language and Dialect Identification 12 Dec 2023 · 0 repositories · arXiv:2312.07338
-
Multilingual self-supervised speech representations improve the speech recognition of low-resource African languages with codeswitching 25 Nov 2023 · 0 repositories · arXiv:2311.15077
-
Modular Speech-to-Text Translation for Zero-Shot Cross-Modal Transfer 5 Oct 2023 · 0 repositories · arXiv:2310.03724
-
Zero Resource Code-switched Speech Benchmark Using Speech Utterance Pairs For Multiple Spoken Languages 4 Oct 2023 · 1 repository · arXiv:2310.03018
-
Indonesian Automatic Speech Recognition with XLSR-53 20 Aug 2023 · 0 repositories · arXiv:2308.11589
-
Allophant: Cross-lingual Phoneme Recognition with Articulatory Attributes 7 Jun 2023 · 1 repository · arXiv:2306.04306
-
Improving the previous state-of-the-art Frisian ASR by fine-tuning XLS-R 31 Mar 2023 · 0 repositories
-
Improving Spoken Language Identification with Map-Mix 16 Feb 2023 · 1 repository · arXiv:2302.08229
-
Improved Self-Supervised Multilingual Speech Representation Learning Combined with Auxiliary Language Information 7 Dec 2022 · 0 repositories · arXiv:2212.03476
-
Automatic Speech Recognition of Low-Resource Languages Based on Chukchi 11 Oct 2022 · 0 repositories · arXiv:2210.05726
-
Cross-lingual Self-Supervised Speech Representations for Improved Dysarthric Speech Recognition 4 Apr 2022 · 0 repositories · arXiv:2204.01670
-
Language Adaptive Cross-lingual Speech Representation Learning with Sparse Sharing Sub-networks 9 Mar 2022 · 0 repositories · arXiv:2203.04583
-
Joint Unsupervised and Supervised Training for Multilingual ASR 15 Nov 2021 · 0 repositories · arXiv:2111.08137
-
Magic dust for cross-lingual adaptation of monolingual wav2vec-2.0 7 Oct 2021 · 0 repositories · arXiv:2110.03560
-
Unsupervised Cross-lingual Representation Learning for Speech Recognition 24 Jun 2020 · 8 repositories · arXiv:2006.13979Syntology 3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified (of 6 harvested samples)
Tasks archive 2025-07-28
20 shown of 38 tasks the archive attaches to papers tagged with this method, by distinct papers. A task without a page in the catalog is plain text.
Usage over time archive 2025-07-28
Components: the archive holds no method-to-method composition, so PwC's Components table cannot be rebuilt; the Papers list carries no Results column for the same reason (the archive does not join its leaderboard rows to method tags).
Categories archive 2025-07-28
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