Massively Multilingual ASR: 50 Languages, 1 Model, 1 Billion Parameters
Open accessThe DOI matches its Crossref record; 4 of the 4 references it cites were found in a registry or an index.
Abstract
We study training a single acoustic model for multiple languages with the aim of improving automatic speech recognition (ASR) performance on low-resource languages, and over-all simplifying deployment of ASR systems that support diverse languages. We perform an extensive benchmark on 51 languages, with varying amount of training data by language(from 100 hours to 1100 hours). We compare three variants of multilingual training from a single joint model without knowing the input language, to using this information, to multiple heads (one per language cluster). We show that multilingual training of ASR models on several languages can improve recognition performance, in particular, on low resource languages. We see 20.9%, 23% and 28.8% average WER relative reduction compared to monolingual baselines on joint model, joint model with language input and multi head model respectively. To our knowledge, this is the first work studying multilingual ASR at massive scale, with more than 50 languages and more than 16,000 hours of audio across them.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
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
Bengio, Y., Louradour, J., Collobert, R., & Weston, J. (2009) · Proceedings of the 26th Annual International Conference on Machine Learning · doi:10.1145/1553374.1553380 · Cited by 5,366 · cited 1×
“For these cases, we introduced a curriculum training [17] based approach, which incrementally adds each language after the model has been trained for a fixed number of iterations or the Character Error Rate (CER) goes below 50% for the previously added language.”
MethodSelf-citationSpecAugment: A Simple Data Augmentation Method for Automatic Speech Recognition
Park, D. S., Chan, W., Zhang, Y., Chiu, C.-C., Zoph, B., Cubuk, E. D., & Le, Q. V. (2019) · Interspeech 2019 · doi:10.21437/interspeech.2019-2680 · Cited by 3,558
Cross-lingual Language Model Pretraining
Lample, G., & Conneau, A. (2019) · arXiv · doi:10.48550/arxiv.1901.07291 · Cited by 1,586
Subword Regularization: Improving Neural Network Translation Models with Multiple Subword Candidates
Kudo, T. (2018) · Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · doi:10.18653/v1/p18-1007 · Cited by 1,021
Cited by
Finetuned Language Models Are Zero-Shot Learners
Wei, J., Bosma, M., Zhao, V. Y., Guu, K., Yu, A. W., Lester, B., Du, N., Dai, A. M., & Le, Q. V. (2021) · arXiv · doi:10.48550/arxiv.2109.01652 · Cited by 1,101
Recent Advances in End-to-End Automatic Speech Recognition
Li, J. (2022) · APSIPA Transactions on Signal and Information Processing · doi:10.1561/116.00000050 · Cited by 395
Room-Across-Room: Multilingual Vision-and-Language Navigation with Dense Spatiotemporal Grounding
Ku, A., Anderson, P., Patel, R., Ie, E., & Baldridge, J. (2020) · Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.18653/v1/2020.emnlp-main.356 · Cited by 274
Challenges in Automatic Speech Recognition for Adults with Cognitive Impairment
Cohn, M., Lanzi, A., Ishihara, Y., Chuah, C.-N., Zellou, G., & Weakley, A. (2026) · Proceedings of the 2026 CHI Conference on Human Factors in Computing Systems · doi:10.1145/3772318.3791581 · Cited by 4
“Additionally, English is considered a ‘high-resource’ language; these are languages that have a large amount of training data to create robust language models (e.g., Mandarin Chinese, Spanish, French) [26, 31, 71].”
Metadata
- Authors
- Pratap, V., Sriram, A., Tomasello, P., Hannun, A., Liptchinsky, V., Synnaeve, G., & Collobert, R.
- Venue
- Interspeech 2020
- Publisher
- ISCA
- Published
- 2020-10-25
- Pages
- 4751-4755
- ISSN
- 2308-457X (ISSN-L)
- OpenAlex
- W3040454670
- Cited by
- 117
- References
- 4
- FWCI
- 7.36
- Type
- conference paper
- Language
- en
- Open access
- green
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
How to cite
Cite CoChat for the checks on this page, and the paper for its own findings.
- This page
- CoChat. (2026). Citation check: Massively Multilingual ASR: 50 Languages, 1 Model, 1 Billion Parameters. https://app.cochat.ai/papers/10.21437/interspeech.2020-2831
- The paper
- Pratap, V., Sriram, A., Tomasello, P., Hannun, A., Liptchinsky, V., Synnaeve, G., & Collobert, R. (2020). Massively Multilingual ASR: 50 Languages, 1 Model, 1 Billion Parameters. Interspeech 2020. https://doi.org/10.21437/interspeech.2020-2831
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.