Iterative Pseudo-Labeling for Speech Recognition
Open accessAbstract
Pseudo-labeling has recently shown promise in end-to-end automatic speech recognition (ASR). We study Iterative Pseudo-Labeling (IPL), a semi-supervised algorithm which efficiently performs multiple iterations of pseudo-labeling on unlabeled data as the acoustic model evolves. In particular, IPL fine-tunes an existing model at each iteration using both labeled data and a subset of unlabeled data. We study the main components of IPL: decoding with a language model and data augmentation. We then demonstrate the effectiveness of IPL by achieving state-of-the-art word-error rate on the Librispeech test sets in both standard and low-resource setting. We also study the effect of language models trained on different corpora to show IPL can effectively utilize additional text. Finally, we release a new large in-domain text corpus which does not overlap with the Librispeech training transcriptions to foster research in low-resource, semi-supervised ASR
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
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?
UIC uses outputs from the previous epoch as hard pseudo-labels for 'unsupervised classification'.
“DINO is also related to UIC [14] that use outputs from the previous epoch as hard pseudo-labels for 'unsupervised classification'.”
From Emerging Properties in Self-Supervised Vision Transformers (2021) · cites this paper as [14]
Cites
“Librispeech: an ASR corpus based on public domain audio books,”
Panayotov, V., Chen, G., Povey, D., & Khudanpur, S. (2015) · 2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) · doi:10.1109/icassp.2015.7178964 · Cited by 6,072 · see citing works
Flagged first, then by citations
Cited by
Sorted by citations
Emerging Properties in Self-Supervised Vision Transformers
Caron, M., Touvron, H., Misra, I., Jegou, H., Mairal, J., Bojanowski, P., & Joulin, A. (2021) · 2021 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv48922.2021.00951 · Cited by 5,638 · see citing works
“This propagation can either be done with hard assignments of labels [41, 78, 79] or with a soft assignment [76].”
BackgroundHuBERT: Self-Supervised Speech Representation Learning by Masked Prediction of Hidden Units
Hsu, W.-N., Bolte, B., Tsai, Y.-H. H., Lakhotia, K., Salakhutdinov, R., & Mohamed, A. (2021) · IEEE/ACM Transactions on Audio, Speech, and Language Processing · doi:10.1109/taslp.2021.3122291 · Cited by 2,983 · see citing works
Self-supervised speech representation learning: A review
Mohamed, A., Lee, H.-Y., Borgholt, L., Havtorn, J. D., Edin, J., Igel, C., Kirchhoff, K., Li, S.-W., Livescu, K., Maaløe, L., et al. (2022) · IEEE Journal of Selected Topics in Signal Processing · doi:10.1109/jstsp.2022.3207050 · Cited by 372 · see citing works
“For comparison, we also show performance from such methods (iterative pseudo labeling (IPL) [63], slimIPL [254], noisy student [62]), as well as the current state of the art—conformer XXL + noisy student [255]—which augments SSL with various advanced techniques including self-training.”
BackgroundMethodResultInfluentialZhang, Y., Park, D. S., Han, W., Qin, J., Gulati, A., Shor, J., Jansen, A., Xu, Y., Huang, Y., Wang, S., et al. (2022) · IEEE Journal of Selected Topics in Signal Processing · doi:10.1109/jstsp.2022.3182537 · Cited by 161 · see citing works
- Authors
- Xu, Q., Likhomanenko, T., Kahn, J., Hannun, A., Synnaeve, G., & Collobert, R.
- Affiliations
- Meta (United States) (US)
- Venue
- Interspeech 2020
- Publisher
- ISCA
- Published
- 2020-10-25
- Pages
- 1006-1010
- ISSN
- 2308-457X (ISSN-L)
- OpenAlex
- W3096338464
- Cited by
- 112
- References
- 1
- Citations by year
- 2026: 3 · 2025: 9 · 2024: 12 · 2023: 23 · 2022: 30 · 2021: 30 · 2020: 5
- FWCI
- 8.40
- Type
- conference paper
- Language
- en
- Open access
- green
- arxiv.org
- Licence
- public-domain
- Locations
- Interspeech (USB) (publishedVersion)
- arXiv (Cornell University) (submittedVersion, public-domain)
- 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 › Artificial Intelligence › Speech and dialogue systems
- Keywords
- semi-supervised learning, speech recognition, acoustic model training, unlabeled data, data augmentation, language model decoding, low-resource speech recognition, LibriSpeech
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
