The DOI matches its Crossref record; 43 of the 43 references it cites were found in a registry or an index; none of the 9 sources its claims cite is checked for support yet.
wav2vec: Unsupervised Pre-Training for Speech Recognition
Open accessAbstract
We explore unsupervised pre-training for speech recognition by learning representations of raw audio. wav2vec is trained on large amounts of unlabeled audio data and the resulting representations are then used to improve acoustic model training. We pre-train a simple multi-layer convolutional neural network optimized via a noise contrastive binary classification task. Our experiments on WSJ reduce WER of a strong character-based log-mel filterbank baseline by up to 36% when only a few hours of transcribed data is available. Our approach achieves 2.43% WER on the nov92 test set. This outperforms Deep Speech 2, the best reported character-based system in the literature while using two orders of magnitude less labeled training data.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
0 of 9 cited sources checked · 0 supported · 0 flagged
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“Thereafter, performance plateaus while training time increases.”
§ WAV2VEC: UNSUPERVISED PRE-TRAINING FOR SPEECH RECOGNITION > 4.3 ABLATIONS
Strength:plain· not yet calibratedn = 10Tests✓ Asserted: passes✓ Checkable: passes? Load-bearing: unclear✓ Based: passesA result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Table 3 shows that increasing the number of negative samples only helps up to ten samples.”
§ WAV2VEC: UNSUPERVISED PRE-TRAINING FOR SPEECH RECOGNITION > 4.3 ABLATIONS
Strength:plain· not yet calibratedCausal:direct· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes? Load-bearing: unclear✓ Based: passesA result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Table 1 shows that pre-training on more data leads to better accuracy on the WSJ benchmark.”
§ WAV2VEC: UNSUPERVISED PRE-TRAINING FOR SPEECH RECOGNITION > 4.1 PRE-TRAINING FOR THE WSJ BENCHMARK
Tests✓ Asserted: passes✓ Checkable: passes✓ Load-bearing: passes✓ Based: passesA result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“On TIMIT, pre-training enables us to match the best reported result in the literature.”
- Also stated in: § 4.2 PRE-TRAINING FOR TIMIT · plain
“Table 2 shows that wav2vec pre-training on Librispeech and WSJ audio data can lead to results matching the state of the art.”
§ WAV2VEC: UNSUPERVISED PRE-TRAINING FOR SPEECH RECOGNITION > 1 INTRODUCTION
Tests✓ Asserted: passes✓ Checkable: passes✓ Load-bearing: passes✓ Based: passes- Also stated in: § 4.2 PRE-TRAINING FOR TIMIT · plain
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Pretrained representations can substantially improve performance over our character-based baseline which is trained on log-mel filterbank features.”
§ WAV2VEC: UNSUPERVISED PRE-TRAINING FOR SPEECH RECOGNITION > 4.1 PRE-TRAINING FOR THE WSJ BENCHMARK
Tests✓ Asserted: passes✓ Checkable: passes✓ Load-bearing: passes✓ Based: passesA result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Table 4 shows that a crop size of 150k frames results in the best performance.”
§ WAV2VEC: UNSUPERVISED PRE-TRAINING FOR SPEECH RECOGNITION > 4.3 ABLATIONS
Strength:plain· not yet calibratedCausal:direct· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes? Load-bearing: unclear✓ Based: passesA result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“We found it important to choose a normalization scheme that is invariant to the scaling and the offset of the input.This choice resulted in representations that generalize well across datasets.”
§ WAV2VEC: UNSUPERVISED PRE-TRAINING FOR SPEECH RECOGNITION > 2 PRE-TRAINING APPROACH
Tests✓ Asserted: passes✓ Checkable: passes✓ Load-bearing: passes✓ Based: passesA result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Experimental results on the WSJ benchmark demonstrate that pre-trained representations estimated on about 1,000 hours of unlabeled speech can substantially improve a character-based ASR system and outperform the best character-based result in the literature, Deep Speech 2, improving WER from 3.1 % to 2.43 %.”
§ WAV2VEC: UNSUPERVISED PRE-TRAINING FOR SPEECH RECOGNITION > 1 INTRODUCTION
Tests✓ Asserted: passes✓ Checkable: passes✓ Load-bearing: passes✓ Based: passes- Rests on an assumption: Unlabeled audio data is much easier to collect than labeled data.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Pre-training only on the audio data of WSJ (wav2vec WSJ) performs worse compared to the much larger Librispeech (wav2vec Libri).”
§ WAV2VEC: UNSUPERVISED PRE-TRAINING FOR SPEECH RECOGNITION > 4.1 PRE-TRAINING FOR THE WSJ BENCHMARK
Strength:plain· not yet calibratedCausal:direct· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes? Load-bearing: unclear✓ Based: passesIn the paper
“Similar tovan den Oord et al. (2018), we found that sampling negatives from different sequences and speakers yields inferior results.”
§ WAV2VEC: UNSUPERVISED PRE-TRAINING FOR SPEECH RECOGNITION > 5 CONCLUSIONS
What the sources say
- Not checked yetcites van den Oord et al., 2018
Tests✓ Asserted: passes✓ Checkable: passes✓ Load-bearing: passes✓ Based: passes
- It may state two separate claims as one. 8
- The quote only partly states this claim. 1
- Probably not a substantial claim. 3
In the paper
“Our approach achieves 2.43 % WER on the nov92 test set.This outperforms Deep Speech 2, the best reported character-based system in the literature while using two orders of magnitude less labeled training data.”
- Also stated in: § 5 CONCLUSIONS · plain
“Our approach achieves 2.43 % WER on the test set of WSJ, a result that outperforms the next best known character-based speech recognition model in the literature (Amodei et al., 2016) while using two orders of magnitude less transcribed training data.”
- Also stated in: § 4.1 PRE-TRAINING FOR THE WSJ BENCHMARK · boosted
“This shows that pre-training on unlabeled audio data can improve over the best character-based approach, Deep Speech 2 (Amodei et al., 2016), by 0.67 WER on nov92.”
§ WAV2VEC: UNSUPERVISED PRE-TRAINING FOR SPEECH RECOGNITION > Abstract
What the sources say
- Not checked yetcites Amodei et al., 2016
Tests✓ Asserted: passes✓ Checkable: passes✓ Load-bearing: passes✓ Based: passesIt may state two separate claims as one. The quote only partly states this claim.
- Also stated in: § 5 CONCLUSIONS · plain
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“We found it important to introduce skip connections in the aggregator to help convergence in this case.”
§ WAV2VEC: UNSUPERVISED PRE-TRAINING FOR SPEECH RECOGNITION > 2 PRE-TRAINING APPROACH
Strength:plain· not yet calibratedCausal:direct· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes✗ Load-bearing: fails✓ Based: passesProbably not a substantial claim. The paper’s conclusions may not depend on it.
In the paper
“In comparison to Hadian et al. (2018), wav2vec performs as well as their phoneme-based model and wav2vec large outperforms it by 0.37 WER.”
§ WAV2VEC: UNSUPERVISED PRE-TRAINING FOR SPEECH RECOGNITION > 4.1 PRE-TRAINING FOR THE WSJ BENCHMARK
What the sources say
- Not checked yetcites Hadian et al., 2018
Load-bearingStrength:plain· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes✓ Load-bearing: passes✓ Based: passesIt may state two separate claims as one.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“We show that more data for pre-training improves performance and that this approach not only improves resource-poor setups, but also settings where all WSJ training data is used.”
§ WAV2VEC: UNSUPERVISED PRE-TRAINING FOR SPEECH RECOGNITION > 5 CONCLUSIONS
Tests✓ Asserted: passes✓ Checkable: passes✓ Load-bearing: passes✓ Based: passesIt may state two separate claims as one.
- Rests on an assumption: Unlabeled audio data is much easier to collect than labeled data.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Table 5 also shows that predicting more than 12 steps ahead in the future does not result in better performance and increasing the number of steps increases training time.”
§ WAV2VEC: UNSUPERVISED PRE-TRAINING FOR SPEECH RECOGNITION > 5 CONCLUSIONS
Tests✓ Asserted: passes✓ Checkable: passes✓ Load-bearing: passes✓ Based: passesIt may state two separate claims as one.
In the paper
“Similar to Hénaff et al. (2019), we noticed that fine-tuning the embedding network does not meaningfully improve performance while substantially increasing the acoustic model training time.”
§ WAV2VEC: UNSUPERVISED PRE-TRAINING FOR SPEECH RECOGNITION > 4.1 PRE-TRAINING FOR THE WSJ BENCHMARK
What the sources say
- Not checked yetcites Hénaff et al., 2019
Strength:plain· not yet calibratedCausal:direct· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes? Load-bearing: unclear✓ Based: passesIt may state two separate claims as one.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Accuracy steadily increases with more data for pre-training and the best accuracy is achieved with the largest amount of data for pre-training.”
§ WAV2VEC: UNSUPERVISED PRE-TRAINING FOR SPEECH RECOGNITION > 4.2 PRE-TRAINING FOR TIMIT
Tests✓ Asserted: passes✓ Checkable: passes✓ Load-bearing: passes✓ Based: passesIt may state two separate claims as one.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“Not restricting the maximum length (None) gives an average sequence length of about 207k frames and results in the worst accuracy.”
§ WAV2VEC: UNSUPERVISED PRE-TRAINING FOR SPEECH RECOGNITION > 4.3 ABLATIONS
Tests✓ Asserted: passes✓ Checkable: passes✓ Load-bearing: passes✓ Based: passesIt may state two separate claims as one.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“wav2vec relies on a fully convolutional architecture which can be easily parallelized over time on modern hardware compared to recurrent models used in previous work ( §2).”
§ WAV2VEC: UNSUPERVISED PRE-TRAINING FOR SPEECH RECOGNITION > 1 INTRODUCTION
Strength:plain· not yet calibratedCausal:direct· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes✗ Load-bearing: fails✓ Based: passesProbably not a substantial claim. The paper’s conclusions may not depend on it. It may state two separate claims as one.
What the paper did — it cites no source for this, so there is none to check. The quote shows it is in the paper.
In the paper
“In this experiment, everything is kept equal except for the number of negative samples.”
§ WAV2VEC: UNSUPERVISED PRE-TRAINING FOR SPEECH RECOGNITION > 4.3 ABLATIONS
Load-bearingStrength:plain· not yet calibratedTests✓ Asserted: passes✓ Checkable: passes✓ Load-bearing: passes✓ Based: passesProbably not a substantial claim.
The paper relies on this without support.
Unlabeled audio data is much easier to collect than labeled data.
“This enables exploiting unlabeled audio data which is much easier to collect than labeled data.”
The paper relies on this without support.
Accurately modeling the data distribution p(x) is a common and challenging problem for these approaches.
“A common problem with these approaches is the requirement to accurately model the data distribution p(x), which is challenging.”
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 source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“As in [15], utilizing the causal convolutional aggregator results in a fully convolutional model, increasing the parallelizability of the pre-training, resulting in faster training times.”
From Investigating Enhancements to Contrastive Predictive Coding for Human Activity Recognition (2023) · cites this paper as [15]
Experimental — accuracy not yet measuredThe source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“we propose to instead utilize multiple causal convolution blocks to perform the autoregressive summarization, due to its simplicity, faster training times, and ease of parallelization that recurrent models do not enjoy.”
From Investigating Enhancements to Contrastive Predictive Coding for Human Activity Recognition (2023) · cites this paper as [15]
Experimental — accuracy not yet measuredThe cited source says what the claim attributes to it.
In the citing paper
“Note that wav2vec directly trains on speech’s raw waveform to extract deep features that represent speech signals.”
From A Survey of Deep Learning-Based Multimodal Emotion Recognition: Speech, Text, and Face (2023) · cites this paper as [54]
The cited source says what the claim attributes to it.
In the citing paper
“For example, Schneider et al. [54] proposed an unsupervised speech pre-training method named wav2vec that only uses unlabeled speech data for self-supervised training to obtain generalized speech features that can be applied to multiple tasks.”
From A Survey of Deep Learning-Based Multimodal Emotion Recognition: Speech, Text, and Face (2023) · cites this paper as [54]
Citations
Cites
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
ImageNet: A large-scale hierarchical image database
Deng, J., Dong, W., Socher, R., Li, L.-J., Li, K., & Fei-Fei, L. (2009) · 2009 IEEE Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2009.5206848 · Cited by 65,333
Microsoft COCO: Common Objects in Context
Lin, T.-Y., Maire, M., Belongie, S., Hays, J., Perona, P., Ramanan, D., Dollár, P., & Zitnick, C. L. (2014) · Lecture Notes in Computer Science · doi:10.1007/978-3-319-10602-1_48 · Cited by 45,460
Distributed Representations of Words and Phrases and their Compositionality
Mikolov, T., Sutskever, I., Chen, K., Corrado, G., & Dean, J. (2013) · arXiv · doi:10.48550/arxiv.1310.4546 · Cited by 24,533
Natural Language Processing (almost) from ScratchPreprint
Collobert, R., Weston, J., Bottou, L., Karlen, M., Kavukcuoglu, K., & Kuksa, P. P. (2011) · arXiv (Cornell University) · doi:10.48550/arxiv.1103.0398 · Cited by 6,920
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
SGDR: Stochastic Gradient Descent with Warm Restarts
Loshchilov, I., & Hutter, F. (2016) · arXiv · doi:10.48550/arxiv.1608.03983 · Cited by 5,309
Unsupervised Visual Representation Learning by Context Prediction
Doersch, C., Gupta, A., & Efros, A. A. (2015) · 2015 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2015.167 · Cited by 2,629
Flagged first, then by citations
Cited by
Sorted by citations
Items 301–400 of 1,003
Knowledge-Aware Bayesian Co-Attention for Multimodal Emotion Recognition
Zhao, Z., Wang, Y., & Wang, Y. (2023) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp49357.2023.10095798 · Cited by 25
Anomaly Detection for In-Vehicle Communication Using Transformers
Cobilean, V., Mavikumbure, H. S., Wickramasinghe, C. S., Varghese, B. J., Pennington, T., & Manic, M. (2023) · Annual Conference of the IEEE Industrial Electronics Society (IECON) · doi:10.1109/iecon51785.2023.10311788 · Cited by 24
Doumbouya, M., Einstein, L., & Piech, C. (2021) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v35i17.17733 · Cited by 28
The History of Speech Recognition to the Year 2030Preprint
Hannun, A. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2108.00084 · Cited by 24
A New Acoustic-Based Pronunciation Distance Measure
Bartelds, M., Richter, C., Liberman, M., & Wieling, M. B. (2020) · Frontiers in Artificial Intelligence · doi:10.3389/frai.2020.00039 · Cited by 23
Large-Scale Self- and Semi-Supervised Learning for Speech Translation
Wang, C., Wu, A., Pino, J., Baevski, A., Auli, M., & Conneau, A. (2021) · Interspeech (USB) · doi:10.21437/interspeech.2021-1912 · Cited by 23
Self-citationBhati, S., Villalba, J., Żelasko, P., Moro-Velázquez, L., & Dehak, N. (2022) · IEEE/ACM Transactions on Audio Speech and Language Processing · doi:10.1109/taslp.2022.3180684 · Cited by 23
A New Amharic Speech Emotion Dataset and Classification Benchmark
Retta, E. A., Almekhlafi, E., Sutcliffe, R. F. E., Mhamed, M., Ali, H., & Feng, J. H. (2022) · ACM Transactions on Asian and Low-Resource Language Information Processing · doi:10.1145/3529759 · Cited by 23
Zolnoori, M., Vergez, S., Kostić, Z., Jonnalagadda, S., McDonald, M. V., Bowles, K. H., & Topaz, M. (2022) · JMIR Human Factors · doi:10.2196/35325 · Cited by 23
End-to-End Speech Translation for Code Switched Speech
Weller, O., Sperber, M., Pires, T., Setiawan, H., Gollan, C., Telaar, D., & Paulik, M. (2022) · Findings of the Association for Computational Linguistics: ACL (Findings of ACL) · doi:10.18653/v1/2022.findings-acl.113 · Cited by 23
Interpretable Representation Learning for Speech and Audio Signals Based on Relevance Weighting
Agrawal, P., & Ganapathy, S. (2020) · IEEE/ACM Transactions on Audio Speech and Language Processing · doi:10.1109/taslp.2020.3030489 · Cited by 25
Klempíř, O., & Krupička, R. (2024) · Sensors · doi:10.3390/s24175520 · Cited by 23
San, N., Bartelds, M., Browne, M., Clifford, L., Gibson, F., Mansfield, J., Nash, D., Simpson, J., Turpin, M., Vollmer, M., et al. (2021) · IEEE Workshop on Automatic Speech Recognition and Understanding (ASRU) · doi:10.1109/asru51503.2021.9688301 · Cited by 27
A Comparative Study of Self-Supervised Speech Representation Based Voice Conversion
Huang, W.-C., Yang, S.-W., Hayashi, T., & Toda, T. (2022) · IEEE Journal of Selected Topics in Signal Processing · doi:10.1109/jstsp.2022.3193761 · Cited by 23
Autoregressive Predictive Coding: A Comprehensive Study
Yang, G.-P., Yeh, S.-L., Chung, Y.-A., Glass, J. R., & Tang, H. (2022) · IEEE Journal of Selected Topics in Signal Processing · doi:10.1109/jstsp.2022.3203608 · Cited by 24
JOIST: A Joint Speech and Text Streaming Model for ASR
Sainath, T. N., Prabhavalkar, R., Bapna, A., Zhang, Y., Huo, Z., Chen, Z., Li, B., Wang, W., & Strohman, T. (2023) · IEEE Spoken Language Technology Workshop (SLT) · doi:10.1109/slt54892.2023.10022774 · Cited by 22
Chen, C., Hong, H., Guo, J., & Song, B. (2023) · IEEE/ACM Transactions on Audio Speech and Language Processing · doi:10.1109/taslp.2023.3263801 · Cited by 22
Defend Data Poisoning Attacks on Voice Authentication
Li, K., Baird, C., & Lin, D. (2023) · IEEE Transactions on Dependable and Secure Computing · doi:10.1109/tdsc.2023.3289446 · Cited by 24
Arasteh, S. T., Ríos-Urrego, C. D., Nöth, E., Maier, A., Yang, S. H., Rusz, J., & Orozco‐Arroyave, J. R. (2023) · Interspeech (USB) · doi:10.21437/interspeech.2023-2108 · Cited by 22
Evidence of Vocal Tract Articulation in Self-Supervised Learning of Speech
Cho, C. J., Wu, P., Mohamed, A., & Anumanchipalli, G. K. (2023) · ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) · doi:10.1109/icassp49357.2023.10094711 · Cited by 21
Improving mispronunciation detection and diagnosis for non- native learners of the Arabic language
Alrashoudi, N., Al-Khalifa, H. S., & Alotaibi, Y. A. (2025) · Discover Computing · doi:10.1007/s10791-024-09489-8 · Cited by 22
Camp: A Two-Stage Approach to Modelling Prosody in Context
Hodari, Z., Moinet, A., Karlapati, S., Lorenzo-Trueba, J., Merritt, T., Joly, A., Abbas, A., Karanasou, P., & Drugman, T. (2021) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp39728.2021.9414413 · Cited by 22
Probing phoneme, language and speaker information in unsupervised speech representations
de Seyssel, M., Lavechin, M., Adi, Y., Emmanuel Dupoux, A., & Wisniewski, G. (2022) · Interspeech (USB) · doi:10.21437/interspeech.2022-373 · Cited by 26
Automatic Speech Recognition for Uyghur, Kazakh, and Kyrgyz: An Overview
Du, W., Maimaitiyiming, Y., Nijat, M., Li, L., Hamdulla, A., & Wang, D. (2022) · Applied Sciences · doi:10.3390/app13010326 · Cited by 22
Improving Medical Speech-to-Text Accuracy using Vision-Language Pre-training Models
Huh, J., Park, S. J., Lee, J. E., & Ye, J. C. (2023) · IEEE Journal of Biomedical and Health Informatics · doi:10.1109/jbhi.2023.3345897 · Cited by 21
On Multimodal Emotion Recognition for Human-Chatbot Interaction in the Wild
Kovačević, N., Holz, C., Groß, M. H., & Wampfler, R. (2024) · INTERNATIONAL CONFERENCE ON MULTIMODAL INTERACTION · doi:10.1145/3678957.3685759 · Cited by 21
Zero-Query Adversarial Attack on Black-box Automatic Speech Recognition Systems
Fang, Z., Wang, T., Zhao, L., Zhang, S., Li, B., Ge, Y., Li, Q. L., Shen, C. Q., & Wang, Q. (2024) · ACM SIGSAC Conference on Computer and Communications Security (CCS) · doi:10.1145/3658644.3670309 · Cited by 21
Deschamps-Berger, T., Lamel, L. F., & Devillers, L. Y. (2022) · INTERNATIONAL CONFERENCE ON MULTIMODAL INTERACTION · doi:10.1145/3536220.3558038 · Cited by 23
Recent Advances in Discrete Speech Tokens: A Review
Guo, Y., Li, Z., Wang, H., Li, B., Shao, C., Zhang, H., Du, C., Xie, C., Liu, S., & Yu, K. (2025) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2025.3643619 · Cited by 58
Lee, C.-C., Chaspari, T., Provost, E. M., & Narayanan, S. S. (2023) · Proceedings of the IEEE · doi:10.1109/jproc.2023.3276209 · Cited by 23
Multimodal Vigilance Estimation With Modality-Pairwise Contrastive Loss
Zhang, M., Luo, Z., Xie, L., Liu, T., Ye, Y., Yao, D., Zhao, S., & Yin, E. (2023) · IEEE Transactions on Biomedical Engineering · doi:10.1109/tbme.2023.3328942 · Cited by 20
A multimodal dynamical variational autoencoder for audiovisual speech representation learning
Sadok, S., Leglaive, S., Laurent Girin, B., Alameda-Pineda, X., & Séguier, R. (2024) · Neural Networks · doi:10.1016/j.neunet.2024.106120 · Cited by 20
MODA: Mapping-Once Audio-driven Portrait Animation with Dual Attentions
Liu, Y., Lin, L., Yu, F., Zhou, C., & Li, Y. (2023) · 2023 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51070.2023.02104 · Cited by 20
Explore the World of Audio Deepfakes: A Guide to Detection Techniques for Non-Experts
Schäfer, K., Choi, J., & Zmudzinski, S. (2024) · ACM International Workshop on Multimedia AI against Disinformation (MAD) · doi:10.1145/3643491.3660289 · Cited by 21
Towards Unsupervised Learning of Speech Features in the Wild
Rivière, M., & Emmanuel Dupoux, A. (2021) · IEEE Spoken Language Technology Workshop (SLT) · doi:10.1109/slt48900.2021.9383461 · Cited by 21
Talk, Don’t Write: A Study of Direct Speech-Based Image Retrieval
Sanabria, R., Waters, A., & Baldridge, J. (2021) · Interspeech (USB) · doi:10.21437/interspeech.2021-96 · Cited by 21
Improving Self-Supervised Learning for Speech Recognition with Intermediate Layer Supervision
Wang, C., Wu, Y., Chen, S., Liu, S., Li, J., Qian, Y., & Yang, Z. (2022) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp43922.2022.9747022 · Cited by 22
Y-Vector: Multiscale Waveform Encoder for Speaker Embedding
Zhu, G., Jiang, F., & Duan, Z. (2021) · Interspeech (USB) · doi:10.21437/interspeech.2021-1707 · Cited by 19
Adaptive multilingual speech recognition with pretrained models
Pham, N.-Q., Waibel, A. H., & Niehues, J. (2022) · Interspeech (USB) · doi:10.21437/interspeech.2022-872 · Cited by 24
Wnet: Audio-Guided Video Object Segmentation via Wavelet-Based Cross- Modal Denoising Networks
Pan, W., Shi, H., Zhao, Z., Zhu, J., He, X., Pan, Z., Gao, L., Yu, J., Wu, F. Q., & Tian, Q. C. (2022) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr52688.2022.00138 · Cited by 19
Gabler, P., Geiger, B. C., Schuppler, B., & Kern, R. (2023) · Information · doi:10.3390/info14020137 · Cited by 24
A Joint Network Based on Interactive Attention for Speech Emotion Recognition
Hu, Y., Hou, S., Yang, H., Huang, H., & He, L. (2023) · IEEE International Conference on Multimedia and Expo (ICME) · doi:10.1109/icme55011.2023.00295 · Cited by 19
Voice user interfaces for effortless navigation in medical virtual reality environments
Hombeck, J., Voigt, H., & Lawonn, K. (2024) · Computers & Graphics · doi:10.1016/j.cag.2024.104069 · Cited by 22
Towards a Competitive End-to-End Speech Recognition for CHiME-6 Dinner Party Transcription
Andrusenko, A., Laptev, A., & Medennikov, I. (2020) · Interspeech (USB) · doi:10.21437/interspeech.2020-1074 · Cited by 19
Leveraging deep learning with audio analytics to predict the success of crowdfunding projects
Shi, J., Yang, K., Xu, W. X., & Wang, M. (2021) · The Journal of Supercomputing · doi:10.1007/s11227-020-03595-2 · Cited by 19
Noisy Student-Teacher Training for Robust Keyword Spotting
Park, H., Zhu, P., Moreno, I. L., & Subrahmanya, N. (2021) · Interspeech (USB) · doi:10.21437/interspeech.2021-72 · Cited by 19
Zheng, G., Xiao, Y., Gong, K., Zhou, P., Liang, X., & Lin, L. (2021) · Findings of the Association for Computational Linguistics: EMNLP (Findings of EMNLP) · doi:10.18653/v1/2021.findings-emnlp.236 · Cited by 20
STATNet: Spectral and Temporal features based Multi-Task Network for Audio Spoofing Detection
Ranjan, R., Vatsa, M., & Singh, R. (2022) · 2022 IEEE International Joint Conference on Biometrics (IJCB) · doi:10.1109/ijcb54206.2022.10007949 · Cited by 18
Polat, H., Turan, A. K., Koçak, C., & Ulaş, H. B. (2024) · Electronics · doi:10.3390/electronics13214227 · Cited by 18
Liu, B., Dong, Q., & Hu, Z. (2021) · Knowledge-Based Systems · doi:10.1016/j.knosys.2021.107337 · Cited by 18
Data Augmentation for ASR Using TTS Via a Discrete Representation
Ueno, S., Mimura, M., Sakai, S., & Kawahara, T. (2021) · IEEE Workshop on Automatic Speech Recognition and Understanding (ASRU) · doi:10.1109/asru51503.2021.9688218 · Cited by 18
Kessler, S., Thomas, B., & Karout, S. A. (2022) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp43922.2022.9747374 · Cited by 19
Improving The Latency And Quality Of Cascaded Encoders
Sainath, T. N., He, Y., Narayanan, A., Botros, R., Wang, W., Qiu, D., Chiu, C., Prabhavalkar, R., Gruenstein, A., Gulati, A., et al. (2022) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp43922.2022.9747879 · Cited by 18
Self-Supervised Pre-Training for Attention-Based Encoder-Decoder ASR Model
Gao, C., Cheng, G., Ta, L., Zhang, P., & Yan, Y. (2022) · IEEE/ACM Transactions on Audio Speech and Language Processing · doi:10.1109/taslp.2022.3171967 · Cited by 18
Self-Supervised Graphs for Audio Representation Learning With Limited Labeled Data
Shirian, A., Somandepalli, K., & Guha, T. (2022) · IEEE Journal of Selected Topics in Signal Processing · doi:10.1109/jstsp.2022.3190083 · Cited by 18
Arunkumar, A., Sukhadia, V. N., & Umesh, S. (2022) · Interspeech (USB) · doi:10.21437/interspeech.2022-11376 · Cited by 18
Cross-Corpus Speech Emotion Recognition with HuBERT Self-Supervised Representation
Pastor, M., Ribas, D., Ortega, A., Miguel, A. D., & Lleida, E. (2022) · IberSPEECH · doi:10.21437/iberspeech.2022-16 · Cited by 19
Exploring WavLM on Speech Enhancement
Song, H., Chen, S., Chen, Z., Wu, Y., Yoshioka, T., Tang, M., Shin, J. W., & Liu, S. (2023) · IEEE Spoken Language Technology Workshop (SLT) · doi:10.1109/slt54892.2023.10023356 · Cited by 20
Evaluating the Performance of wav2vec Embedding for Parkinson's Disease Detection
Klempíř, O., Příhoda, D., & Krupička, R. (2023) · Measurement Science Review · doi:10.2478/msr-2023-0033 · Cited by 19
Modality-collaborative Transformer with Hybrid Feature Reconstruction for Robust Emotion Recognition
Chen, C., & Zhang, P. (2024) · ACM Transactions on Multimedia Computing Communications and Applications · doi:10.1145/3640343 · Cited by 18
Unified Cross-Modal Attention: Robust Audio-Visual Speech Recognition and Beyond
Li, J., Li, C., Wu, Y., & Qian, Y. (2024) · IEEE/ACM Transactions on Audio Speech and Language Processing · doi:10.1109/taslp.2024.3375641 · Cited by 18
ScanTalk: 3D Talking Heads from Unregistered Scans
Nocentini, F., Besnier, T., Ferrari, C., Arguillère, S., Berretti, S., & Daoudi, M. (2024) · Lecture notes in computer science · doi:10.1007/978-3-031-73397-0_2 · Cited by 18
Multi-view Self-supervised Learning and Multi-scale Feature Fusion for Automatic Speech Recognition
Zhao, J., Li, R., Tian, M., & An, W. (2024) · Neural Processing Letters · doi:10.1007/s11063-024-11614-z · Cited by 18
Speech Emotion Recognition Using Dual-Stream Representation and Cross-Attention Fusion
Yu, S., Meng, J., Fan, W., Chen, Y., Zhu, B., Yu, H., Xie, Y., & Sun, Q. (2024) · Electronics · doi:10.3390/electronics13112191 · Cited by 18
Let’s Go Real Talk: Spoken Dialogue Model for Face-to-Face Conversation
Park, S. J., Kim, C., Rha, H., Kim, M., Hong, J. H., Yeo, J. H., & Ro, Y. M. (2024) · Proceedings of the conference - Association for Computational Linguistics. Meeting · doi:10.18653/v1/2024.acl-long.860 · Cited by 37
Improving Low-Resource Speech Recognition Based on Improved NN-HMM Structures
Sun, X., Yang, Q., Liu, S., & Yuan, X. (2020) · IEEE Access · doi:10.1109/access.2020.2988365 · Cited by 19
Chen, X., Zhu, Q., Zhang, J., & Dai, L.-R. (2022) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp43922.2022.9746205 · Cited by 18
Simple and Effective Multimodal Learning Based on Pre-Trained Transformer Models
Miyazawa, K., Kyuragi, Y., & Nagai, T. (2022) · IEEE Access · doi:10.1109/access.2022.3159346 · Cited by 19
An Ensemble-Learning-Based Technique for Bimodal Sentiment Analysis
Shah, S., Ghomeshi, H., Vakaj, E., Cooper, E., & Mohammad, R. (2023) · Big Data and Cognitive Computing · doi:10.3390/bdcc7020085 · Cited by 21
Foundation Models and Biometrics: A Survey and Outlook
Shahreza, H. O., & Marcel, S. (2025) · IEEE Transactions on Information Forensics and Security · doi:10.1109/tifs.2025.3602233 · Cited by 20
Chen, Z., Zhang, Y., Rosenberg, A., Ramabhadran, B., Moreno, P. J., & Wang, G. (2022) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp43922.2022.9746475 · Cited by 17
Deep fusion framework for speech command recognition using acoustic and linguistic features
Mehra, S., & Susan, S. (2023) · Multimedia Tools and Applications · doi:10.1007/s11042-023-15118-1 · Cited by 17
Avoiding dominance of speaker features in speech-based depression detection
Zuo, L., & Mak, M. (2023) · Pattern Recognition Letters · doi:10.1016/j.patrec.2023.07.016 · Cited by 17
AfriSpeech-200: Pan-African Accented Speech Dataset for Clinical and General Domain ASR
Olatunji, T., Afonja, T., Yadavalli, A., Emezue, C. C., Singh, S., Dossou, B. F. P., Osuchukwu, J., Osei, S., Tonja, A. L., Etori, N. A., et al. (2023) · Transactions of the Association for Computational Linguistics · doi:10.1162/tacl_a_00627 · Cited by 24
Modeling early phonetic acquisition from child-centered audio data
Lavechin, M., de Seyssel, M., Métais, M., Metze, F., Mohamed, A., Bredin, H., Emmanuel Dupoux, A., & Cristià, A. (2024) · Cognition · doi:10.1016/j.cognition.2024.105734 · Cited by 23
Oral English Speech Recognition Based on Enhanced Temporal Convolutional Network
Wu, H., & Sangaiah, A. K. (2021) · Intelligent Automation & Soft Computing · doi:10.32604/iasc.2021.016457 · Cited by 17
Transfer Ability of Monolingual Wav2vec2.0 for Low-resource Speech Recognition
Cheng, Y., Wang, J., Cheng, N., Zhou, S., & Xu, B. (2021) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn52387.2021.9533587 · Cited by 17
Simple and Effective Unsupervised Speech Translation
Wang, C., Inaguma, H., Chen, P., Kulikov, I., Tang, Y., Hsu, W.-N., Auli, M., & Pino, J. (2023) · Proceedings of the conference - Association for Computational Linguistics. Meeting · doi:10.18653/v1/2023.acl-long.602 · Cited by 19
Self-citationAccent-Robust Automatic Speech Recognition Using Supervised and Unsupervised Wav2vec EmbeddingsPreprint
Li, J., Manohar, V., Chitkara, P., Tjandra, A., Picheny, M., Zhang, F., Zhang, X., & Saraf, Y. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2110.03520 · Cited by 18
Text-Free Prosody-Aware Generative Spoken Language Modeling
Kharitonov, E., Lee, A., Polyak, A., Adi, Y., Copet, J., Lakhotia, K., Nguyen, T.-A., Rivière, M., Mohamed, A., Dupoux, E., et al. (2021) · arXiv · doi:10.48550/arxiv.2109.03264 · Cited by 16
Contrastive Semi-Supervised Learning for ASR
Xiao, A., Fuegen, C., & Mohamed, A. (2021) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp39728.2021.9414079 · Cited by 16
Understanding How Pretraining Regularizes Deep Learning Algorithms
Yao, Y., Yu, B., Gong, C., & Liu, T. (2021) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2021.3131377 · Cited by 16
Language Adaptive Cross-Lingual Speech Representation Learning with Sparse Sharing Sub-Networks
Lu, Y., Huang, M., Qu, X., Wei, P., & Ma, Z. (2022) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp43922.2022.9747671 · Cited by 16
Indonesian Automatic Speech Recognition with XLSR-53
Arisaputra, P., & Zahra, A. (2022) · Ingénierie des systèmes d information · doi:10.18280/isi.270614 · Cited by 18
Pace-Adaptive and Noise-Resistant Contrastive Learning for Multimodal Feature Fusion
Guo, X., Kot, A. C., & Kong, A. W. (2023) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2023.3252270 · Cited by 17
BLASER: A Text-Free Speech-to-Speech Translation Evaluation Metric
Chen, M., Duquenne, P.-A., Andrews, P., Kao, J., Mourachko, A., Schwenk, H., & Costa‐jussà, M. R. (2023) · Proceedings of the conference - Association for Computational Linguistics. Meeting · doi:10.18653/v1/2023.acl-long.504 · Cited by 21
Stochastic Latent Talking Face Generation Toward Emotional Expressions and Head Poses
Sheng, Z., Nie, L., Zhang, M., Chang, X., & Yan, Y. (2023) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2023.3311039 · Cited by 16
Yang, J., Dong, X., & Du, X. (2023) · Journal of King Saud University - Computer and Information Sciences · doi:10.1016/j.jksuci.2023.101791 · Cited by 16
Attention-Based Speech Enhancement Using Human Quality Perception Modeling
Nayem, K. M., & Williamson, D. S. (2023) · IEEE/ACM Transactions on Audio Speech and Language Processing · doi:10.1109/taslp.2023.3328282 · Cited by 16
Zuo, L., Mak, M., & Tu, Y. (2024) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp48485.2024.10448231 · Cited by 17
Open-Emotion: A Reproducible EMO-Superb For Speech Emotion Recognition Systems
Wu, H., Chou, H.-C., Chang, K.-W., Goncalves, L., Du, J., Jang, J. R., Lee, C.-C., & Lee, H.-Y. (2024) · IEEE Spoken Language Technology Workshop (SLT) · doi:10.1109/slt61566.2024.10832296 · Cited by 17
A Comparison of Supervised and Unsupervised Pre-Training of End-to-End Models
Misra, A., Hwang, D., Huo, Z., Garg, S., Siddhartha, N., Narayanan, A., & Sim, K. C. (2021) · Interspeech (USB) · doi:10.21437/interspeech.2021-654 · Cited by 16
SNRi Target Training for Joint Speech Enhancement and Recognition
Koizumi, Y., Karita, S., Narayanan, A., Panchapagesan, S., & Bacchiani, M. (2022) · Interspeech (USB) · doi:10.21437/interspeech.2022-302 · Cited by 16
Open set classification of sound event
You, J., Wu, W., & Lee, J. (2024) · Scientific Reports · doi:10.1038/s41598-023-50639-7 · Cited by 16
Towards Inadequately Pre-trained Models in Transfer Learning
Deng, A., Li, X., Hu, D., Wang, T., Xiong, H., & Xu, C. (2023) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51070.2023.01777 · Cited by 17
FantasyTalking: Realistic Talking Portrait Generation via Coherent Motion Synthesis
Wang, M., Wang, Q., Jiang, F., Fan, Y., Zhang, Y., Qi, Y., Zhao, K., & Xu, M. (2025) · ACM International Conference on Multimedia (ACM MM) · doi:10.1145/3746027.3755217 · Cited by 57
Gender Neutralisation for Unbiased Speech Synthesising
Rizhinashvili, D., Sham, A. H., & Anbarjafari, G. (2022) · Electronics · doi:10.3390/electronics11101594 · Cited by 15
Li, J., Hasegawa‐Johnson, M., & McElwain, N. L. (2023) · Interspeech (USB) · doi:10.21437/interspeech.2023-460 · Cited by 15
MelHuBERT: A Simplified Hubert on Mel Spectrograms
Lin, T.-Q., Lee, H.-Y., & Tang, H. (2023) · IEEE Workshop on Automatic Speech Recognition and Understanding (ASRU) · doi:10.1109/asru57964.2023.10389700 · Cited by 15
Acoustic Emission in Ceramic Matrix Composites
Tulshibagwale, N., Brodnik, N. R., Muir, C., Hilmas, A. M., Kiser, J. D., Smith, C., Almansour, A. S., Presby, M. J., & Daly, S. H. (2024) · Applied Mechanics Reviews · doi:10.1115/1.4064763 · Cited by 15
Metadata
- Authors
- Schneider, S., Baevski, A., Collobert, R., & Auli, M.
- Affiliations
- Technical University of Munich (DE)
- Meta (Israel) (IL)
- Venue
- Interspeech 2019
- Publisher
- ISCA
- Published
- 2019-09-15
- Pages
- 3465-3469
- ISSN
- 2308-457X (ISSN-L)
- OpenAlex
- W2939710050
- Cited by
- 1,290
- References
- 32
- Citations by year
- 2026: 86 · 2025: 169 · 2024: 222 · 2023: 262 · 2022: 221 · 2021: 225 · 2020: 97 · 2019: 7
- FWCI
- 52.61
- 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) (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
- wav2vec, unsupervised pre-training, speech recognition, audio representation learning, noise contrastive estimation, acoustic model training, convolutional neural networks, Wall Street Journal
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.
A language model drew the claims from the paper on 2026-09-28, under version 3 of the claim definition (model deepseek-v4.1-flash, prompt extract-v3).
A second model labelled each claim on 2026-09-28 (model jev-1.13-20260917, definition revision gold-guideline-v0.2).
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
