Comparative Layer-Wise Analysis of Self-Supervised Speech Models
The DOI matches its Crossref record; 7 of the 7 references it cites were found in a registry or an index.
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.
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?
In the citing paper
“Recent work has shown that S3M representations capture various types of information, from non-linguistic one such as acoustic (Pasad et al., 2023) and speaker (Fan et al., 2021) information to linguistic one such as phonological (Martin et al., 2023;Bentum et al., 2025), lexical (Pasad et al., 2024), syntactic (He et al., 2025), and semantic (wen Yang et al., 2021) information.”
From JPhonABX: Japanese Phonological Discrimination Dataset for Moraic and Accentual Minimal Pairs (2026) · cites this paper as Pasad et al., 2023
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
“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
WavLM: Large-Scale Self-Supervised Pre-Training for Full Stack Speech Processing
Chen, S., Wang, C., Chen, Z., Wu, Y., Liu, S., Chen, Z., Li, J., Kanda, N., Yoshioka, T., Xiao, X., et al. (2022) · IEEE Journal of Selected Topics in Signal Processing · doi:10.1109/jstsp.2022.3188113 · Cited by 1,926
Attention is not not Explanation
Wiegreffe, S., & Pinter, Y. (2019) · Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP) · doi:10.18653/v1/d19-1002 · Cited by 966 · cited 1×
“The relative unreliability of layer weights as an analysis tool is not too surprising and is similar to findings for attention weights in NLP models [25, 26].”
ResultSUPERB: Speech Processing Universal PERformance Benchmark
Yang, S.-W., Chi, P.-H., Chuang, Y.-S., Lai, C.-I. J., Lakhotia, K., Lin, Y. Y., Liu, A. T., Shi, J., Chang, X., Lin, G.-T., et al. (2021) · Interspeech 2021 · doi:10.21437/interspeech.2021-1775 · Cited by 681
Unsupervised Cross-Lingual Representation Learning for Speech Recognition
Conneau, A., Baevski, A., Collobert, R., Mohamed, A., & Auli, M. (2021) · Interspeech 2021 · doi:10.21437/interspeech.2021-329 · Cited by 637
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 · cited 2×
“Self-supervised models have become a nearly ubiquitous approach for learning speech representations and improving performance on downstream tasks [1–5], but our understanding of their properties and strategies for their use is still limited.”
BackgroundSelf-citationLayer-Wise Analysis of a Self-Supervised Speech Representation Model
Pasad, A., Chou, J.-C., & Livescu, K. (2021) · 2021 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU) · doi:10.1109/asru51503.2021.9688093 · Cited by 262
Self-citation
Research works printed but not linked: 17
- baevski, 2020, wav2vec 2.0: A framework for self-supervised learning of speech representations, NeurIPS
- 10.1109/ICASSP43922.2022.9747103 · DOI
- peng, 2022, Self-supervised representation learning for speech using visual grounding and masked language modeling, AAAI Workshop on Self-supervised Learning for Audio and Speech Processing
- borgholt, 2022, A brief overview of unsupervised neural speech representation learning, AAAI Workshop on Self-supervised Learning for Audio and Speech Processing
- 10.1109/ICASSP39728.2021.9414460 · DOI
- 10.2307/2333955 · DOI · Paper page
- shi, 2022, Learning audio-visual speech representation by masked multimodal cluster prediction, ICLRE
- 10.1109/ICASSP43922.2022.9747432 · DOI
- 10.1109/ICASSP39728.2021.9414321 · DOI
- morcos, 2018, Insights on representational similarity in neural networks with canonical correlation, NeurIPS
- 10.18653/v1/2020.emnlp-main.588 · DOI
- jain, 2019, Attention is not explanation, NAACL
- 10.18653/v1/2022.findings-emnlp.422 · DOI
- li, 2022, Exploration of a self-supervised speech model: A study on emotional corpora, SLT
- suwon, 2022, SLUE: New benchmark tasks for spoken language understanding evaluation on natural speech, ICASSP
- 10.21437/Interspeech.2021-1280 · DOI · Paper page
- 10.18653/v1/2022.acl-long.580 · DOI
Cited by
JPhonABX: Japanese Phonological Discrimination Dataset for Moraic and Accentual Minimal Pairs
Koga, Y., Kando, S., & Miyao, Y. (2026) · Findings of the Association for Computational Linguistics: EMNLP 2026 · doi:10.18653/2026.findings-emnlp.1072
Metadata
- Authors
- Pasad, A., Shi, B., & Livescu, K.
- Affiliations
- Toyota Technological Institute at Chicago
- Venue
- ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
- Publisher
- IEEE
- Published
- 2023-06-04
- Pages
- 1-5
- Cited by
- 105
- References
- 7
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: Comparative Layer-Wise Analysis of Self-Supervised Speech Models. https://app.cochat.ai/papers/10.1109/icassp49357.2023.10096149
- The paper
- Pasad, A., Shi, B., & Livescu, K. (2023). Comparative Layer-Wise Analysis of Self-Supervised Speech Models. ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). https://doi.org/10.1109/icassp49357.2023.10096149
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.