The DOI matches its Crossref record; 54 of the 54 references it cites were found in a registry or an index.
Unsupervised Cross-Lingual Representation Learning for Speech Recognition
Open accessAbstract
This paper presents XLSR which learns cross-lingual speech representations by pretraining a single model from the raw waveform of speech in multiple languages. We build 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 resulting model is fine-tuned on labeled data and experiments show that cross-lingual pretraining significantly outperforms monolingual pretraining. On the CommonVoice benchmark, XLSR shows a relative phoneme error rate reduction of 72% compared to the best known results. On BABEL, our approach improves word error rate by 16% relative compared to a comparable system. Our approach enables a single multilingual speech recognition model which is competitive to strong individual models. Analysis shows that the latent discrete speech representations are shared across languages with increased sharing for related languages. We hope to catalyze research in low-resource speech understanding by releasing XLSR-53, a large model pretrained in 53 languages.
Overview
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
The cited source says what the claim attributes to it.
In the citing paper
“Depending on the number of languages used for training, XLSR supports 53 languages (XLSR [124]) and 128 languages (XLS-R [125]).”
From Audio Deepfake Detection: What Has Been Achieved and What Lies Ahead (2025) · cites this paper as [124]
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A. N., Kaiser, L., & Polosukhin, I. (2017) · arXiv · doi:10.48550/arxiv.1706.03762 · Cited by 120,404
Adam: A Method for Stochastic Optimization
Kingma, D. P., & Ba, J. (2014) · arXiv · doi:10.48550/arxiv.1412.6980 · Cited by 98,946
BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
Devlin, J., Chang, M.-W., Lee, K., & Toutanova, K. (2018) · arXiv · doi:10.48550/arxiv.1810.04805 · Cited by 73,173
Momentum Contrast for Unsupervised Visual Representation LearningPreprint
He, K., Fan, H., Wu, Y., Xie, S., & Girshick, R. B. (2019) · Computer Vision and Pattern Recognition · doi:10.48550/arxiv.1911.05722 · Cited by 16,250
Momentum Contrast for Unsupervised Visual Representation Learning
He, K., Fan, H., Wu, Y., Xie, S., & Girshick, R. (2020) · 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr42600.2020.00975 · Cited by 13,347
Deep Contextualized Word Representations
Peters, M., Neumann, M., Iyyer, M., Gardner, M., Clark, C., Lee, K., & Zettlemoyer, L. (2018) · Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long Papers) · doi:10.18653/v1/n18-1202 · Cited by 11,983
A simple framework for contrastive learning of visual representations
Chen, T., Kornblith, S., Norouzi, M., & Hinton, G. (2020) · arXiv · doi:10.48550/arxiv.2002.05709 · Cited by 10,857
Representation Learning with Contrastive Predictive Coding
Oord, A. V. D., Li, Y., & Vinyals, O. (2018) · arXiv · doi:10.48550/arxiv.1807.03748 · Cited by 6,242
Unsupervised Cross-lingual Representation Learning at Scale
Conneau, A., Khandelwal, K., Goyal, N., Chaudhary, V., Wenzek, G., Guzmán, F., Grave, E., Ott, M., Zettlemoyer, L., & Stoyanov, V. (2020) · Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics · doi:10.18653/v1/2020.acl-main.747 · Cited by 5,637
Self-citationGraves, A., Fernández, S., Gomez, F., & Schmidhuber, J. (2006) · Proceedings of the 23rd international conference on Machine learning - ICML '06 · doi:10.1145/1143844.1143891 · Cited by 5,370
Flagged first, then by citations
Research works printed but not linked: 2
- Mark JF Gales, Kate M Knill, and Anton Ragni. Low-resource speech recognition and keyword- spotting. In Proc. of SPECOM, pp. 3-19. Springer, 2017.
- Yonglong Tian, Dilip Krishnan, and Phillip Isola. Contrastive multiview coding. arXiv, 2019.
Cited by
Sorted by citations
Items 601–635 of 635
Multilingual Speech Emotion Recognition Using End-to-End Multilingual Pre-trained Model
Das, A., & Haque, M. A. (2025) · IEEE International Conference on Signal Processing, Information, Communication and Systems (SPICSCON) · doi:10.1109/spicscon69221.2025.11504192
Comparative Eval. of SSL Feature Extractors & Classifiers for DFAD
Park, S.-B., & Song, H.-M. (2026) · Lecture notes in computer science · doi:10.1007/978-981-95-6857-4_24
Schuster, T., Trögele, J., Döring, N., Krüger, R., Hoffmann, M., & Friedrich, H. (2026) · Lecture notes in business information processing · doi:10.1007/978-3-032-26363-6_21
Moape, T. G., & Moyo, N. N. (2026) · doi:10.1109/icnlp69856.2026.11527646
A Lightweight Multimodal Architecture for Punctuation Restoration in Kazakh ASR
Karibayeva, A., Myssov, O., Abduali, B., Amirova, D., & Karybayeva, A. (2026) · Computers · doi:10.3390/computers15060345
Fine-tuning and script normalization for enhancing Malayalam automatic speech recognition
Pillai, L. G., Manohar, K., Baiju, B., & Sherly, E. (2026) · AIP conference proceedings · doi:10.1063/5.0338077
The BOOL.I Corpus: The Impact of Context on Child and Adolescent Bengali ASR
Husain, K., Preity, S., Sohan, M. R., Hossain, A., & Rahman, M. S. (2026) · IEEE International Conference on Quantum Photonics, Artificial Intelligence & Networking (QPAIN) · doi:10.1109/qpain69676.2026.11546536
Narasimha, V., Onkar, A., Naidu, M. B., & Gururaj, C. (2026) · International Conference on Integrated Intelligence and Communication Systems (ICIICS) · doi:10.1109/iciics67880.2026.11483613
TURK-SER: A Speech Emotion Recognition Dataset and Benchmark for Turkish
Eriş, M., Eriş, F. G., & Akbal, E. (2026) · International Journal of Innovative Engineering Applications · doi:10.46460/ijiea.1887612 · Cited by 1
Palivela, H., Narvekar, M., & Mukhopadhyay, D. (2026) · Communications in computer and information science · doi:10.1007/978-3-032-27120-4_27
Canuto, T., Sardenberg, E., Mann, P., Utino, M. Y. R., COUTINHO, D. J. B., Uchôa, A., & Pereira, J. A. (2026) · International Workshop on Cooperative and Human Aspects of Software Engineering (CHASE) · doi:10.1145/3794860.3794910
Ullah, A., Muhammad, Y., & Zhang, R. (2026) · Lecture notes in computer science · doi:10.1007/978-981-92-2862-1_20
Fine-tuning Whisper model for end-to-end Kannada to English speech transcription
Holla, K. R., Agam, R., Martis, B. G., Martis, B. G., N., M. S., & Ganiga, R. (2026) · Open Computer Science · doi:10.1515/comp-2025-0060
Enhancing Persian Speech Emotion Recognition with Contrastive Learning and Multimodal Fusion
Esmaeili, M., & Sabeti, V. (2025) · International Conference on Information and Knowledge Technology (IKT) · doi:10.1109/ikt69652.2025.11626665
SpeakEZ: Self Supervised Feature Extractor Based Dysarthric ASR System
Tiwari, S., Tejani, K., Prajapati, A., & Kasat, D. (2026) · International Conference on Speech, Multimodal and Advanced Communication Systems (ICSMACS) · doi:10.1109/icsmacs68968.2026.11628520
Muthu, M., Sasikala, E., & Girirajan, S. (2026) · International Conference on Data Science and Business Systems (ICDSBS) · doi:10.1109/icdsbs69077.2026.11634690
MultiMed-ST datasets for machine translation in medical applications
Gouda, G., & Suma, R. (2026) · Journal of Ambient Intelligence and Humanized Computing · doi:10.1007/s12652-026-05120-4
Chaabi, Y., & Oubenal, M. (2026) · International Conference on Emerging Smart Technologies and Applications (eSmarTA) · doi:10.1109/esmarta70636.2026.11652212
Magar, B., Shinde, T., Chougule, M. N., & Dane, B. (2026) · Journal of Electrical Systems and Information Technology · doi:10.1186/s43067-026-00365-7
GRASS - HRI: A Corpus of Spontaneous Austrian German Dialogues with the Social Robot Furhat
Lennkh, S., Paierl, M., & Schuppler, B. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37249-9_42
On the Robustness to Recording Condition of Speaker and Accent Embeddings for a Voice Cloning System
Martin, P., Guennec, D., Barreaud, V., Barbot, N., & Lolive, D. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37249-9_28
Dar, M. A., Kammula, S. G. K., Pushparaj, J., & Santhosh, V. S. (2026) · Frontiers in Artificial Intelligence · doi:10.3389/frai.2026.1883049
Cross-lingual Robustness of Zipformer: Czech and German ASR Benchmarking Study
Lehečka, J., Šmídl, L., Psutka, J., Ircing, P., & Psutka, J. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37867-5_2
Swaroop, D., Thenkanidiyoor, V., Dileep, A. D., & Muralikrishna, H. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37867-5_29
Sequential Domain Adaptation of Whisper for Kazakh Academic Lecture Speech Recognition
Kozhirbayev, Z., & Yessenbayev, Z. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37867-5_6
Effect of the Amount of Training Data in Speech Emotion Recognition
Halmai, D., & Gosztolya, G. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37870-5_4
Taha, M., Hatem, A., Abdelmohsen, M., & Kadry, R. (2026) · Intelligent Methods, Systems, and Applications (IMSA) · doi:10.1109/imsa70415.2026.11700272
Fairness and Explainability in Portuguese Audio Deepfake Detection: The Effect of Audio Codecs
Nagpal, R., Rinaldo, G., Simons, K., Silva, C. O., Pereira, L. V. A. S., Xing, L., & Gupta, A. D. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-39892-5_9
Automatic Speech Recognition for Low-Resource Creole Languages: An Empirical Study on Kreol Morisien
Yarroo, B., Gobin-Rahimbux, B., & Pudaruth, S. (2026) · International Conference on Next Generation Computing Applications (NextComp) · doi:10.1109/nextcomp70574.2026.11708006
Juiz, G. T., Cândido, A., Pinhanez, C. S., & Lima, R. D. F. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-39904-5_4
Harnessing XLSR for Spoken Language Identification in Indian Languages
Joe, A., Rajan, A. K., Shaju, A. P., Menon, D. S., & Ambili, A. R. (2026) · International Conference on Innovations in Engineering and Technology (ICIET) · doi:10.1109/iciet70550.2026.11712622
Multilingual Motion Memory Adaptation for Turkish 3D Talking Faces
Temiz, H., Gökberk, B., & Akarun, L. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-39388-3_21 · Cited by 1
Besra: An interactive tool for speech annotation, phonetic analysis, and computer-assisted fieldwork
van Dam, K. P., Snee, D., List, J., Goderich, A., Ciucci, L., Meloni, C. Y., Thaam, K., Muheim, N., Bocklage, K., & Rubehn, A. (2026) · Open Research Europe · doi:10.12688/openreseurope.25173.1
Charif, K., & Sabri, L. (2026) · Research Square · doi:10.21203/rs.3.rs-10022445/v1
Mirza, S., Nugraha, A., Luthfiarta, A., Zeniarja, J., Farsainsa, R. D., & Ramadhan, F. P. (2026) · International Seminar on Application for Technology of Information and Communication (iSemantic) · doi:10.1109/isemantic71495.2026.11742850
Metadata
- Authors
- Conneau, A., Baevski, A., Collobert, R., Mohamed, A., & Auli, M.
- Affiliations
- Meta (United Kingdom) (GB)
- ORCID
- Auli, Michael
- Venue
- Interspeech 2021
- Publisher
- ISCA
- Published
- 2021-08-30
- Pages
- 2426-2430
- ISSN
- 2308-457X (ISSN-L)
- OpenAlex
- W3037057938
- Cited by
- 637
- References
- 47
- Citations by year
- 2026: 60 · 2025: 136 · 2024: 115 · 2023: 155 · 2022: 103 · 2021: 61
- FWCI
- 50.12
- Type
- conference paper
- Language
- en
- Open access
- green
- arxiv.org
- Locations
- Interspeech (USB) (publishedVersion)
- arXiv (Cornell University) (submittedVersion)
- arXiv (Cornell University)
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Speech Recognition and Synthesis
- Physical Sciences › Computer Science › Signal Processing › Speech and Audio Processing
- Physical Sciences › Computer Science › Signal Processing › Music and Audio Processing
- Keywords
- cross-lingual representation learning, multilingual speech recognition, XLS-R, wav2vec 2.0, contrastive learning, shared latent representation, Common Voice, Babel
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
