SUPERB: Speech Processing Universal PERformance Benchmark
The DOI matches its Crossref record; 41 of the 41 references it cites were found in a registry or an index.
Abstract
Self-supervised learning (SSL) has proven vital for advancing research in natural language processing (NLP) and computer vision (CV).The paradigm pretrains a shared model on large volumes of unlabeled data and achieves state-of-the-art (SOTA) for various tasks with minimal adaptation.However, the speech processing community lacks a similar setup to systematically explore the paradigm.To bridge this gap, we introduce Speech processing Universal PERformance Benchmark (SUPERB).SUPERB is a leaderboard to benchmark the performance of a shared model across a wide range of speech processing tasks with minimal architecture changes and labeled data.Among multiple usages of the shared model, we especially focus on extracting the representation learned from SSL for its preferable re-usability.We present a simple framework to solve SUPERB tasks by learning task-specialized lightweight prediction heads on top of the frozen shared model.Our results demonstrate that the framework is promising as SSL representations show competitive generalizability and accessibility across SUPERB tasks.We release SUPERB as a challenge with a leaderboard 1 and a benchmark toolkit 2 to fuel the research in representation learning and general speech processing.
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?
The cited source says what the claim attributes to it.
In the citing paper
“According to [14], the authors have also indicated that by weighting the representations of different layers, self-supervised model has shown great potential in various speech downstream tasks.”
From Audio Deepfake Detection With Self-Supervised WavLM And Multi-Fusion Attentive Classifier (2024) · cites this paper as [14]
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
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
Self-citationBERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
Devlin, J., Chang, M.-W., Lee, K., & Toutanova, K. (2019) · Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers) · doi:10.18653/v1/n19-1423 · Cited by 54,325
Self-citationDeep 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
Self-citationRepresentation 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
“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
GLUE: A Multi-Task Benchmark and Analysis Platform for Natural Language Understanding
Wang, A., Singh, A., Michael, J., Hill, F., Levy, O., & Bowman, S. (2018) · Proceedings of the 2018 EMNLP Workshop BlackboxNLP: Analyzing and Interpreting Neural Networks for NLP · doi:10.18653/v1/w18-5446 · Cited by 4,222
IEMOCAP: Interactive emotional dyadic motion capture database
Busso, C., Bulut, M., Lee, C.-C., Kazemzadeh, A., Mower, E., Kim, S., Chang, J. N., Lee, S., & Narayanan, S. S. (2008) · Language Resources and Evaluation · doi:10.1007/s10579-008-9076-6 · Cited by 3,869
HuBERT: 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
Self-citationDeep Clustering for Unsupervised Learning of Visual Features
Caron, M., Bojanowski, P., Joulin, A., & Douze, M. (2018) · Lecture Notes in Computer Science · doi:10.1007/978-3-030-01264-9_9 · Cited by 2,674
X-Vectors: Robust DNN Embeddings for Speaker Recognition
Snyder, D., Garcia-Romero, D., Sell, G., Povey, D., & Khudanpur, S. (2018) · 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) · doi:10.1109/icassp.2018.8461375 · Cited by 2,620
Research works printed but not linked: 2
- [13][13] A. Baevski, S. Schneider, and M. Auli, 'vq-wav2vec: Selfsupervised learning of discrete speech representations,' in ICLR , 2020. -
- [25][25] X. Anguera, L. Rodriguez-Fuentes, A. Buzo, F. Metze, I. Sz¨ oke, and M. Penagarikano, 'Quesst2014: Evaluating query-byexample speech search in a zero-resource setting with real-life queries,' in ICASSP , 2015, pp. 5833-5837. -
Cited by
Items 701–756 of 756
Auditory Illusion Benchmark for Large Audio Language Models
Kim, H., Hong, E., & Lee, K. (2026) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp55912.2026.11462423
Self-citationContent-Preserving Speech Representation Learning Via Adaptive Segment-Level Alignment
Dong, L., Wang, W., Yu, Z., Xiang, Y., Xian, Y., & Huang, Y. (2026) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp55912.2026.11462234
Han, S., Lee, S., & Lee, K. (2026) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp55912.2026.11462163
Self-citationFrom Pretraining to Robustness: Benchmarking SSL Models for Noise-Robust Speech Emotion Recognition
Eleftheriou, S., Γιαννακόπουλος, Θ., Stafylakis, T., & Androutsopoulos, I. (2026) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp55912.2026.11464378
Reasoning Driven Captions to Assist Noise Robust Speech Emotion Recognition
Chunarkar, S. B., & Lee, C.-C. (2026) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp55912.2026.11460654
EmU: Emotion Understanding - A Naturalistic Multimodal Dataset and Benchmark
Newman, M. S., Priyasad, D., Denman, S., Senadji, B., Fernando, T., White, K. M., & Fookes, C. (2026) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp55912.2026.11462348
Xie, J., & Hansen, J. H. L. (2026) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp55912.2026.11464722
Evaluating Compositional Structure in Audio Representations
Chen, C., Steers, B., McFee, B., & Bello, J. P. (2026) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp55912.2026.11465018 · Cited by 1
Meghanani, A., & Hain, T. (2026) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp55912.2026.11462377
Spatially Aware Self-Supervised Models for Multi-Channel Neural Speaker Diarization
Han, J., Wang, R., Masuyama, Y., Delcroix, M., Rohdin, J., Du, J., & Burget, L. (2026) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp55912.2026.11463023
Dubey, H., & Kadwal, M. (2026) · International Journal For Multidisciplinary Research · doi:10.36948/ijfmr.2026.v08i03.77483
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
JODAL: Joint Domain Adversarial Learning for TTS-Augmented Automatic Speech Recognition
Kim, J.-W., & Jung, H. (2026) · Mathematics · doi:10.3390/math14101669
Benchmarking Foundation Models for Cross-Domain Speaker Profiling
Moradi, A., & Falk, T. H. (2026) · IEEE Conference on Artificial Intelligence (CAI) · doi:10.1109/cai68641.2026.11536565
Pimentel, A., Zhu, Y. M., & Falk, T. H. (2026) · IEEE Conference on Artificial Intelligence (CAI) · doi:10.1109/cai68641.2026.11536622
MACA: Multi-Axis Covariance Alignment for Robust Distillation of Self-Supervised Speech Models
Kim, D.-H., Lee, J.-H., & Chang, J.-H. (2026) · IEEE Transactions on Audio Speech and Language Processing · doi:10.1109/taslpro.2026.3703215
Arystanbekov, B., Maxutov, A., Nurimanov, A., & Varol, H. A. (2026) · Big Data and Cognitive Computing · doi:10.3390/bdcc10060192 · Cited by 1
Guo, L., Zhou, B., & Xing, D. (2026) · Journal of Medical and Biological Engineering · doi:10.1007/s40846-026-01040-y
Group-Wise Layer Aggregation of Self-Supervised Representations for Speech Emotion Recognition
Park, S., Kim, H. S., & Kong, K. (2026) · IEEE Signal Processing Letters · doi:10.1109/lsp.2026.3707494
Wang, C., Wu, J., Ren, S., Lin, J., Wang, G., & Zhang, J. (2026) · Communications in computer and information science · doi:10.1007/978-981-92-0199-0_4
Kumar, S., Ghosh, S., Lin, Y., Sakshi, S., Seth, A., Chen, Y., Duraiswami, R., & Manocha, D. (2026) · Findings of the Association for Computational Linguistics: ACL (Findings of ACL) · doi:10.18653/v1/2026.findings-acl.2101 · Cited by 3
Self-citationLillini, D., Thebaud, T., Migliorelli, L., Dehak, N., Squartini, S., & Velazquez, L. M. (2026) · The Speaker and Language Recognition Workshop (Odyssey) · doi:10.21437/odyssey.2026-38
Voice, Speech, and Large Language Models in Neurology: From Acoustic Biomarkers to Conversational AI
Shelly, S. (2026) · Computation · doi:10.3390/computation14070160
Enhancing speech emotion recognition using statistical self-supervised embeddings
Chakhtouna, A., Sekkate, S., & Adib, A. (2026) · Multimedia Tools and Applications · doi:10.1007/s11042-026-21812-7 · Cited by 1
Cross-domain Fine-Tuned Wav2Vec 2.0 model with Bidirectional GRU for Audio Deepfake Detection
Sharma, B. B., Selwal, A., & Gupta, T. (2026) · International Conference on Electronics, Computers and Artificial Intelligence (ECAI) · doi:10.1109/ecai69016.2026.11613791
Reducing Speaker Leakage in Voice Conversion Using Speaker-Invariant Representation
Beirami, A. S., & Homayounpour, M. M. (2026) · International Interdisciplinary Conference on Artificial Intelligence: Engineering, Health, Finance and Humanities (IICAI) · doi:10.1109/iicai70155.2026.11620707
Khanna, P., Sambangi, S., Vijaya Saraswathi, R., Ravuri, V., & Vuppala, A. K. (2026) · International Conference on Signal Processing and Communications (SPCOM) · doi:10.1109/spcom71105.2026.11622994
Are Speech Language Models More Noise Robust for Zero Shot Children's Speech Recognition
Das, A., Sinha, A., & Kathania, H. K. (2026) · International Conference on Signal Processing and Communications (SPCOM) · doi:10.1109/spcom71105.2026.11623001
Huang, S., Zhang, J., Xu, J., Zhang, Q., Li, Z., Wang, S., Qiu, Z., Xiong, Z., Liang, J., & Fu, C. (2026) · Sensors · doi:10.3390/s26165050
Pathirana, N., Htait, A., & Wanner, E. F. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-35390-0_24
Hu, K., Fan, X., Hu, Y., Li, J., Lee, B., Hasegawa‐Johnson, M., & McElwain, N. L. (2026) · Developmental Science · doi:10.1111/desc.70251
Diffusion-Based Generative Regularization for Cross-Modal Supervised Learning
Asakura, T., Inoue, N., & Shinoda, K. (2026) · IEEE Access · doi:10.1109/access.2026.3724724
Abdullah, A., Ather, M. A., Fatima, Z., Kolesnikova, O., & Sidorov, G. (2026) · Scientific Reports · doi:10.1038/s41598-026-69201-2
Byalal, R. M., Das, S., & Kumaresan, M. (2026) · International Journal of Artificial Intelligence and Machine Learning · doi:10.51483/ijaiml.6.9s.2026.1383-1396
CEDAR: Cepstral Evidence and Dynamic Acoustic Refinement for Speech Emotion Recognition
Hussain, A., Zaheer, A., Hussain, I., & Gu, Y. (2026) · International Conference on Computer Information Science and Application Technology (CISAT) · doi:10.1109/cisat71030.2026.11682607
Yakovenko, A., & Shuranov, E. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37870-5_2
Frame-Adaptive Layer Aggregation of Pre-Trained Speech Encoders for Speaker Verification
Kim, J. S., Park, H. J., Shin, W., & Han, S. W. (2026) · IEEE Signal Processing Letters · doi:10.1109/lsp.2026.3735272
Uteuliev, N., Kudaybergenov, J., Kudaybergenov, T., Rakhimovich, M. A., & Khudaybergenov, K. K. (2026) · Information · doi:10.3390/info17101048
Speech–Text Fusion With ASR Reliability Metadata for Speech Emotion Recognition
Wan, K. (2026) · IEEE Access · doi:10.1109/access.2026.3737228
Oliinyk, V., & Асланова, В. (2026) · Адаптивні системи автоматичного управління · doi:10.20535/1560-8956.50.2026.372291
Breathing Signal Prediction from Speech: Toward Reproducible and Comparable Models
Pessanha, F., Wildt, G., MacIntyre, A. D., Kaya, H., & Salah, A. A. A. (2026) · INTERNATIONAL CONFERENCE ON MULTIMODAL INTERACTION · doi:10.1145/3776574.3831208
Zheng, Z., Pargoo, N. S., Akash, K., & Misu, T. (2026) · INTERNATIONAL CONFERENCE ON MULTIMODAL INTERACTION · doi:10.1145/3776574.3831226
Shaffi, S. A., Seikavandi, M. J., Obara, A., Modica, A., & Narcizo, F. B. (2026) · Companion Publication of the International Conference on Multimodal Interaction (ICMI Companion) · doi:10.1145/3776591.3837049 · Cited by 1
StutterSense: A Real-Time, Context-Aware Intended Word Prediction System for Disfluent Speakers
Aswin, S., Advaith, B., Rajeev, D., & Kolil, V. K. (2026) · IEEE World Conference on Applied Intelligence and Computing (AIC) · doi:10.1109/aic70896.2026.11717154
Guijosa, L. C., Martinez, F. L., & Echave, J. M. S. (2026) · Documento ocasional/Documento ocasional - Banco de España · doi:10.53479/44665
Kim, S.-B., Kim, K.-W., & Yu, H.-J. (2026) · IEEE Access · doi:10.1109/access.2026.3742554
Layer-Wise Evaluation of Self-Supervised Speech Representations for Emotion Recognition
Klunda, P. S., Jakubec, M., & Jarina, R. (2026) · International Conference Radioelektronika · doi:10.1109/radioelektronika71189.2026.11726409
Speech Emotion Recognition via Attentive Pooling on Whisper Encoder Representations
Gantulga, M.-E., Munkhnasan, Z., Orgil, J., & Uurtsaikh, M. (2026) · International Symposium on Computer Science and Educational Technology (ISCSET) · doi:10.1109/iscset70652.2026.11722990
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
Ferreira, A. I. S., Gris, L. R. S., de Oliveira, F. S., Filho, A. R. G., & Soares, A. D. S. (2026) · doi:10.18653/2026.salma-1.10
Jabnoun, J., & Zrigui, M. (2026) · Procedia Computer Science · doi:10.1016/j.procs.2026.09.085
Unsupervised Speech in the Wild Challenge: Learning Robust Multilingual Representations
Gómez, R. M., Rodríguez, J. F., Galvez, D., & Luger, S. K. K. (2026) · Interspeech (USB) · doi:10.21437/interspeech.2026-3113
SSL-based Sequence Matching for Unsupervised Audio Retrieval
Quatra, M. L., Koudounas, A., & Siniscalchi, S. M. (2026) · Interspeech (USB) · doi:10.21437/interspeech.2026-2369
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
- 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., Huang, T.-H., Tseng, W.-C., Lee, K.-T., Liu, D.-R., Huang, Z., Dong, S., Li, S.-W., Watanabe, S., Mohamed, A., & Lee, H.-Y.
- Affiliations
- National Taiwan University (TW)
- Meta (United States) (US)
- Johns Hopkins University (US)
- Carnegie Mellon University (US)
- Amazon (United States) (US)
- ORCID
- Venue
- Interspeech 2021
- Publisher
- ISCA
- Published
- 2021-08-30
- Pages
- 1194-1198
- ISSN
- 2308-457X (ISSN-L)
- OpenAlex
- W3197580070
- Cited by
- 681
- References
- 40
- Citations by year
- 2026: 67 · 2025: 138 · 2024: 157 · 2023: 205 · 2022: 108 · 2021: 6
- FWCI
- 54.87
- Type
- conference paper
- Language
- en
- Open access
- closed
- Locations
- Interspeech (USB) (publishedVersion)
- 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 › Domain Adaptation and Few-Shot Learning
- Keywords
- self-supervised learning, speech processing, benchmark, shared models, representation learning, frozen pre-trained models, task generalization
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
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.