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 601–700 of 1,003
An Automatic Speaker Clustering Pipeline for the Air Traffic Communication Domain
Khalil, D., Prasad, A., Motlíček, P., Zuluaga-Gómez, J., Nigmatulina, I., Madikeri, S. R., & Schuepbach, C. (2023) · Aerospace · doi:10.3390/aerospace10100876 · Cited by 7
Building robust Korean speech recognition model by fine-tuning large pretrained model*
Oh, C., Kim, C., & Park, K. (2023) · Phonetics and Speech Sciences · doi:10.13064/ksss.2023.15.3.075 · Cited by 7
When can I Speak? Predicting initiation points for spoken dialogue agents
Li, S., Paranjape, A., & Manning, C. D. (2022) · Annual Meeting of the Special Interest Group on Discourse and Dialogue · doi:10.18653/v1/2022.sigdial-1.22 · Cited by 7
Cheng, Z., Niu, F., Lin, Y., Cheng, Z.-Q., Peng, X., & Zhang, B. (2024) · International Workshop on Semantic Evaluation (SemEval) · doi:10.18653/v1/2024.semeval-1.97 · Cited by 14
Training ASR Models By Generation of Contextual Information
Singh, K., Okhonko, D., Liu, J., Wang, Y., Zhang, F., Girshick, R., Edunov, S., Peng, F., Saraf, Y., Zweig, G., et al. (2020) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp40776.2020.9053527 · Cited by 8
Unsupervised Pre-Training for Voice Activation
Kolesau, A., & Šešok, D. (2020) · Applied Sciences · doi:10.3390/app10238643 · Cited by 7
Spoken Term Detection and Relevance Score Estimation Using Dot-Product of Pronunciation Embeddings
Švec, J., Šmídl, L., Psutka, J., & Pražák, A. (2021) · Interspeech (USB) · doi:10.21437/interspeech.2021-1704 · Cited by 7
Time-Domain Joint Training Strategies of Speech Enhancement and Intent Classification Neural Models
Ali, M. N., Falavigna, D., & Brutti, A. (2022) · Sensors · doi:10.3390/s22010374 · Cited by 7
Computational sociophonetics using automatic speech recognition
Coto‐Solano, R. (2022) · Language and Linguistics Compass · doi:10.1111/lnc3.12474 · Cited by 8
Improving the Cross-Lingual Generalisation in Visual Question Answering
Nooralahzadeh, F., & Sennrich, R. (2023) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v37i11.26574 · Cited by 8
Bridging the Granularity Gap for Acoustic Modeling
Xu, C., Zhang, Y., Jiao, C., Liu, X., Hu, C., Zeng, X., Xiao, T., Ma, A., Wang, H., & Zhu, J. (2023) · Findings of the Association for Computational Linguistics: ACL (Findings of ACL) · doi:10.18653/v1/2023.findings-acl.688 · Cited by 7
Neural Model Reprogramming with Similarity Based Mapping for Low-Resource Spoken Command Recognition
Yen, H., Ku, P.-J., Yang, C.-H. H., Hu, H., Siniscalchi, S. M., Chen, P., & Tsao, Y. (2023) · Interspeech (USB) · doi:10.21437/interspeech.2023-1086 · Cited by 7
Integrating Auxiliary Information in Self-supervised LearningPreprint
Tsai, Y.-H. H., Li, T., Liu, W., Liao, P., Salakhutdinov, R., & Morency, L. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2106.02869 · Cited by 12
Shibano, T., Zhang, X., Li, M. T., Cho, H., Sullivan, P., & Abdul-Mageed, M. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2110.00678 · Cited by 7
Speech Representation Learning Through Self-supervised Pretraining And Multi-task FinetuningPreprint
Chen, Y., Yang, S.-W., Lee, C., See, S. C. W., & Lee, H.-Y. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2110.09930 · Cited by 11
Learning Speaker Representation with Semi-supervised Learning approach for Speaker ProfilingPreprint
Rajaa, S., Tung, P. V., & Siong, C. E. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2110.13653 · Cited by 7
Progressive channel fusion for more efficient TDNN on speaker verification
Zhao, Z., Li, Z., Wang, W., & Ji, X. (2024) · Speech Communication · doi:10.1016/j.specom.2024.103105 · Cited by 6
Parra-Gallego, L. F., Arias‐Vergara, T., & Orozco‐Arroyave, J. R. (2024) · Digital Signal Processing · doi:10.1016/j.dsp.2024.104820 · Cited by 6
Improving Pretrained YAMNet for Enhanced Speech Command Detection via Transfer Learning
Lachenani, S., Kheddar, H., & Zmirli, M. O. (2024) · International Conference on Telecommunications and Intelligent Systems (ICTIS) · doi:10.1109/ictis62692.2024.10894266 · Cited by 6
Advancing Spanish Speech Emotion Recognition: A Comprehensive Benchmark of Pre-Trained Models
Mares, A., Diaz-Arango, G. U., Perez-Jacome-Friscione, J., Vázquez-Leal, H., Hernández-Martínez, L., Huerta-Chua, J., Alvarado, A. F. J., & Dominguez-Chavez, J. A. (2025) · Applied Sciences · doi:10.3390/app15084340 · Cited by 6
Kuhn, K., Kersken, V., & Zimmermann, G. (2025) · CHI Conference Extended Abstracts on Human Factors in Computing Systems (CHI EA) · doi:10.1145/3706599.3719984 · Cited by 6
Zhou, D., Zhang, Y., Wu, J., Zhang, X., Xie, L., & Yin, E. (2025) · IEEE Transactions on Human-Machine Systems · doi:10.1109/thms.2025.3585165 · Cited by 6
Teles, A. S., Chaturvedi, J., Wang, T., Scazufca, M., Msosa, Y. J., Stahl, D. R., & Roberts, A. (2025) · PLOS mental health. · doi:10.1371/journal.pmen.0000488 · Cited by 8
Zhuang, Y., Liu, M., Zhang, Y., Deng, J., & Ren, F. (2026) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v40i3.37212 · Cited by 6
Self-Supervised Approach for Few-shot Hand Gesture Recognition
Kimura, N. (2022) · ACM Symposium on User Interface Software and Technology (UIST) · doi:10.1145/3526114.3558707 · Cited by 6
Exploring Diverse Feature Extractions for Adversarial Audio Detection
Choi, Y., Park, J.-G., Lee, J., & Kim, H. (2023) · IEEE Access · doi:10.1109/access.2023.3234110 · Cited by 6
A Lightweight End-to-End Speech Recognition System on Embedded Devices
Wang, Y., & Nishizaki, H. (2023) · IEICE Transactions on Information and Systems · doi:10.1587/transinf.2022edp7221 · Cited by 6
SR-HuBERT : An Efficient Pre-Trained Model for Speaker Verification
Li, Y., Huang, H., Chen, Z., Guan, W., Lin, J., Li, L., & Hong, Q. (2024) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp48485.2024.10447606 · Cited by 7
CAM: A cross-lingual adaptation framework for low-resource language speech recognition
Hu, Q., Zhang, Y., Zhang, X., Han, Z., & Yu, X. (2024) · Information Fusion · doi:10.1016/j.inffus.2024.102506 · Cited by 6
Fusing linguistic and acoustic information for automated forensic speaker comparison
Sergidou, E.-K., Ypma, R. J. F., Rohdin, J., Worring, M., Geradts, Z., & Bosma, W. (2024) · Science & Justice · doi:10.1016/j.scijus.2024.07.001 · Cited by 8
Active Dendrites Enable Efficient Continual Learning in Time-To-First-Spike Neural Networks
Pes, L., Luiken, R., Corradi, F., & Frenkel, C. (2024) · IEEE International Conference on Artificial Intelligence Circuits and Systems (AICAS) · doi:10.1109/aicas59952.2024.10595872 · Cited by 8
Yang, B., & Li, X. (2024) · IEEE/ACM Transactions on Audio Speech and Language Processing · doi:10.1109/taslp.2024.3458811 · Cited by 6
wav2vec-S: Adapting Pre-trained Speech Models for Streaming
Fu, B., Fan, K., Liao, M., Chen, Y., Shi, X., & Huang, Z. (2024) · Findings of the Association for Computational Linguistics: ACL (Findings of ACL) · doi:10.18653/v1/2024.findings-acl.681 · Cited by 6
Li, X., & Zhang, Z. (2024) · Digital Communications and Networks · doi:10.1016/j.dcan.2024.10.007 · Cited by 6
Support of Migrant Reception, Integration, and Social Inclusion by Intelligent Technologies
Wanner, L., Bowen, D., Burgos, M. G., Carrasco, E., Černocký, J., Codina, T., Danilins, J., Davey, S., de Lara, J., Dimopoulou, E., et al. (2024) · Information · doi:10.3390/info15110686 · Cited by 6
FAST: Fast Audio Spectrogram Transformer
Naman, A., & Zhang, G. (2025) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp49660.2025.10889238 · Cited by 6
A Knowledge Distillation-Based Approach to Speech Emotion Recognition
Zhao, Z., Liu, J., Wang, H., Bandara, D., & Tao, J. (2025) · IEEE Transactions on Affective Computing · doi:10.1109/taffc.2025.3574178 · Cited by 6
Ortiz-Pérez, D., Benavent-Lledó, M., Garcia-Rodriguez, J., Tomás, D., & Vizcaya-Moreno, M. F. (2025) · Applied Soft Computing · doi:10.1016/j.asoc.2025.113787 · Cited by 6
A Survey on Foundation Models for Personalized Federated Intelligence
Qiao, Y., Le, H. Q., Raha, A. D., Tran, P.-N., Adhikary, A., Zhang, M., Nguyen, L. X., Huh, E., Niyato, D. T., & Hong, C. S. (2026) · ACM Computing Surveys · doi:10.1145/3844947 · Cited by 9
Improving Reverberant Speech Separation with Synthetic Room Impulse Responses
Aralikatti, R. C., Ratnarajah, A. J., Tang, Z., & Manocha, D. (2021) · IEEE Workshop on Automatic Speech Recognition and Understanding (ASRU) · doi:10.1109/asru51503.2021.9688203 · Cited by 6
Sun, T., Gong, S., Wang, Z., Smith, C. D., Wang, X., Xu, L., & Liu, J. (2021) · International Conference on Machine Learning and Applications · doi:10.1109/icmla52953.2021.00163 · Cited by 6
Self-Supervised Audio-and-Text Pre-training with Extremely Low-Resource Parallel Data
Kang, Y., Liu, T., Li, H., Hao, Y., & Ding, W. (2022) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v36i10.21334 · Cited by 6
MIDISpace: Finding Linear Directions in Latent Space for Music Generation
Turker, M., Dirik, A., & Yanardag, P. (2022) · Creativity and Cognition · doi:10.1145/3527927.3532790 · Cited by 7
Evaluating Variants of wav2vec 2.0 on Affective Vocal Burst Tasks
Atmaja, B. T., & Sasou, A. (2023) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp49357.2023.10096552 · Cited by 6
Comparison of Soft and Hard Target RNN-T Distillation for Large-Scale ASR
Hwang, D., Sim, K. C., Zhang, Y., & Strohman, T. (2023) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp49357.2023.10096418 · Cited by 6
Adaptive Knowledge Distillation Between Text and Speech Pre-Trained Models
Ni, J., Ma, Y., Wang, W., Chen, Q., Ng, D., Han, L., Nguyen, T. H., Zhang, C., Ma, B., & Cambria, E. (2023) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp49357.2023.10096950 · Cited by 6
Li, Z., Wu, Z., Rao, Z., YuHao, X., Guo, J., Wei, D., Shang, H., Minghan, W., Chen, X., Yu, Z., et al. (2023) · International Conference on Spoken Language Translation (IWSLT) · doi:10.18653/v1/2023.iwslt-1.14 · Cited by 6
Spoken Language Identification System for English-Mandarin Code-Switching Child-Directed Speech
Gupta, S. K., Hiray, S., & Kukde, P. (2023) · Interspeech (USB) · doi:10.21437/interspeech.2023-1335 · Cited by 6
ADAPT-TTS: HIGH-QUALITY ZERO-SHOT MULTI-SPEAKER TEXT-TO-SPEECH ADAPTIVE-BASED FOR VIETNAMESE
Ngoc, P. P., Quang, C. T., & Luong, M. C. (2023) · Journal of Computer Science and Cybernetics · doi:10.15625/1813-9663/18136 · Cited by 6
Learning Aligned Audiovisual Representations for Multimodal Sentiment Analysis
Ding, C., Zong, D., Li, B., Zheng, K., Zhou, D., Li, J., & Zhou, Q. (2023) · International Workshop on Multimodal and Responsible Affective Computing (MRAC) · doi:10.1145/3607865.3613184 · Cited by 6
Parkinson’s disease diagnostics using ai and natural language knowledge transfer
Chronowski, M., Kłaczyński, M., Dec‐Ćwiek, M., & Porębska, K. (2023) · Diagnostyka · doi:10.29354/diag/176931 · Cited by 6
Minisuperb: Lightweight Benchmark for Self-Supervised Speech Models
Wang, Y., Chen, H.-Y., Chang, K., Hsu, W. H., & Lee, H.-Y. (2023) · IEEE Workshop on Automatic Speech Recognition and Understanding (ASRU) · doi:10.1109/asru57964.2023.10389699 · Cited by 7
Joint Prediction and Denoising for Large-Scale Multilingual Self-Supervised Learning
Chen, W., Shi, J., Yan, B., Berrebbi, D., Zhang, W., Peng, Y., Chang, X., Maiti, S., & Watanabe, S. (2023) · IEEE Workshop on Automatic Speech Recognition and Understanding (ASRU) · doi:10.1109/asru57964.2023.10389735 · Cited by 7
Alsaggaf, I., Buchan, D. W. A., & Wan, C. (2023) · Briefings in Functional Genomics · doi:10.1093/bfgp/elad059 · Cited by 6
Addressing Data Scarcity in Voice Disorder Detection with Self-Supervised Models
Gupta, R., Madill, C., Gunjawate, D. R., Nguyên, D. D., & Jin, C. T. (2024) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp48485.2024.10446075 · Cited by 6
Uncertainty as a Predictor: Leveraging Self-Supervised Learning for Zero-Shot MOS Prediction
Ravuri, A., Cooper, E., & Yamagishi, J. (2024) · IEEE International Conference on Acoustics, Speech, and Signal Processing Workshops (ICASSPW) · doi:10.1109/icasspw62465.2024.10626267 · Cited by 6
Transfer Learning for End-to-End ASR to Deal with Low-Resource Problem in Persian Language
Kermanshahi, M. A., Akbari, A., & Nasersharif, B. (2021) · International Computer Conference, Computer Society of Iran (CSICC) · doi:10.1109/csicc52343.2021.9420540 · Cited by 6
Yang, L., Fu, K., Zhang, J., & Shinozaki, T. (2021) · Neural Networks · doi:10.1016/j.neunet.2021.07.017 · Cited by 6
Evaluation of Automatic Speech Recognition Systems
Sampaio, M. X., Magalhães, R. P., da Silva, T. L. C., Cruz, L. A., de Vasconcelos, D. R., de Macêdo, J. A. F., & Ferreira, M. G. F. (2021) · Simpósio Brasileiro de Bancos de Dados (SBBD) · doi:10.5753/sbbd.2021.17889 · Cited by 6
Learning from Limited Data for Speech-based Traumatic Brain Injury (TBI) Detection
Ditthapron, A., Agu, E., & Lammert, A. C. (2021) · International Conference on Machine Learning and Applications · doi:10.1109/icmla52953.2021.00239 · Cited by 7
Analysis of natural language processing technology: modern problems and approaches
Kazakova, M. A., & Султанова, А. П. (2022) · Advanced Engineering Research · doi:10.23947/2687-1653-2022-22-2-169-176 · Cited by 8
A Method Improves Speech Recognition with Contrastive Learning in Low-Resource Languages
Sun, L., Yolwas, N., & Jiang, L. (2023) · Applied Sciences · doi:10.3390/app13084836 · Cited by 6
CTCBERT: Advancing Hidden-Unit Bert with CTC Objectives
Fan, R., Wang, Y., Gaur, Y., & Li, J. (2023) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp49357.2023.10094922 · Cited by 7
MASRI-HEADSET: A Maltese Corpus for Speech RecognitionPreprint
Mena, C. D. H., Albert Gatt, A., DeMarco, A., Borg, C., van der Plas, L., Muscat, A., & Padovani, I. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2008.05760 · Cited by 6
Self-supervised Pre-training Reduces Label Permutation Instability of Speech Separation.Preprint
Huang, S.-F., Chuang, S.-P., Liu, D.-R., Chen, Y., Yang, G.-P., & Lee, H.-Y. (2020) · arXiv (Cornell University) · Cited by 6
Towards Semi-Supervised Semantics Understanding from SpeechPreprint
Lai, C.-I., Cao, J. L., Bodapati, S., & Li, S.-W. D. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2011.06195 · Cited by 6
NoiseVC: Towards High Quality Zero-Shot Voice ConversionPreprint
Wang, S., & Borth, D. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2104.06074 · Cited by 9
Scalable Data Annotation Pipeline for High-Quality Large Speech Datasets DevelopmentPreprint
Liu, M., Zhang, C., Xing, H., Feng, C., Chen, M., Bishop, J., & Ngapo, G. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2109.01164 · Cited by 7
Self-supervised Contrastive Cross-Modality Representation Learning for Spoken Question AnsweringPreprint
You, C., Chen, N., & Zou, Y. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2109.03381 · Cited by 9
MIMCL: Multilayer Interaction Module with Contrastive Learning for Speech Emotion Recognition
Li, F., Liu, R., & Wang, B. (2025) · International Conference on Multimedia Retrieval · doi:10.1145/3731715.3733388 · Cited by 5
Li, Z., Liu, Y., Yang, C., Zhou, Y., & Hu, S. (2025) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2025.3590929 · Cited by 5
Brain-to-text decoding with context-aware neural representations and large language models
Li, J., Le, T., Fan, C., Chen, M., & Shlizerman, E. (2025) · Journal of Neural Engineering · doi:10.1088/1741-2552/adfab1 · Cited by 9
MASKSER: A Robust Emotion Recognition Model Based on Voice Data and Noisy Transcripts
Yoon, Y. C., & Kim, S. K. (2025) · IEEE Transactions on Audio Speech and Language Processing · doi:10.1109/taslpro.2025.3617234 · Cited by 5
Azadmaleki, H., Haghbin, Y., Rashidi, S., Nezhad, M. J. M., Zolnour, A., & Zolnoori, M. (2025) · npj Digital Medicine · doi:10.1038/s41746-025-02026-x · Cited by 5
Deori, S., Chutia, T., Saikia, H. J., Boro, A., & Baruah, N. (2025) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2025.113255 · Cited by 5
A Wav2Vec2 model-based automatic speech recognition system for low-resource Kashmiri language
Dar, M. A., & Pushparaj, J. (2025) · International Journal of Speech Technology · doi:10.1007/s10772-025-10228-7 · Cited by 6
Investigating Pre-trained Audio Encoders in the Low-Resource Condition
Yang, H., Zhao, J., Haffari, G., & Shareghi, E. (2023) · Interspeech (USB) · doi:10.21437/interspeech.2023-343 · Cited by 10
Joint spatio-temporal features constrained self-supervised electrocardiogram representation learning
Ran, A., & Liu, H. (2023) · Biomedical Engineering Letters · doi:10.1007/s13534-023-00329-0 · Cited by 5
Fusing Modality-Specific Representations and Decisions for Multimodal Emotion Recognition
Ruan, Y.-P., Han, S., Li, T., & Wu, Y. (2024) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp48485.2024.10447035 · Cited by 5
Conditional selection with CNN augmented transformer for multimodal affective analysis
Wang, J., Wang, S., Xiao, S., Lin, R., Dong, M., & Guo, W. (2024) · CAAI Transactions on Intelligence Technology · doi:10.1049/cit2.12320 · Cited by 5
Teledrive: An Embodied AI Based Telepresence System
Banerjee, S., Paul, S., Roychoudhury, R. D., Bhattacharya, A., Sarkar, C., Sau, A., Pramanick, P., & Bhowmick, B. (2024) · Journal of Intelligent & Robotic Systems · doi:10.1007/s10846-024-02124-0 · Cited by 5
Speech Recognition Models in Assisting Medical History
Gonçalves, Y. T., Alves, J. V. B., Sá, B. A. D., da Silva, L. N., de Macêdo, J. A. F., & da Silva, T. L. C. (2024) · Simpósio Brasileiro de Bancos de Dados (SBBD) · doi:10.5753/sbbd.2024.240270 · Cited by 5
Li, Y., Wang, Y., Hoi, L. M., Yang, D., & Im, S. (2025) · EURASIP Journal on Audio Speech and Music Processing · doi:10.1186/s13636-024-00388-w · Cited by 5
Sang, M., & Hansen, J. H. L. (2025) · IEEE Transactions on Audio Speech and Language Processing · doi:10.1109/taslpro.2025.3539005 · Cited by 5
Futaisi, N. D. A., Schuller, B. W., Ringeval, F., & Pantić, M. (2025) · Frontiers in Digital Health · doi:10.3389/fdgth.2025.1274675 · Cited by 5
Premalatha, S., Kumar, V., Jagini, N. P., & Reddy, G. V. S. (2023) · Signal Image and Video Processing · doi:10.1007/s11760-023-02639-3 · Cited by 5
A Comparative Study of Self-Supervised Speech Representations in Read and Spontaneous TTS
Wang, S., Henter, G. E., Gustafson, J., & Székely, É. (2023) · IEEE International Conference on Acoustics, Speech, and Signal Processing Workshops (ICASSPW) · doi:10.1109/icasspw59220.2023.10193157 · Cited by 5
Task-based Meta Focal Loss for Multilingual Low-resource Speech Recognition
Chen, Y., Zhang, W., Zhang, H., Qu, D., & Yang, X. (2023) · ACM Transactions on Asian and Low-Resource Language Information Processing · doi:10.1145/3626187 · Cited by 5
Investigation of Ensemble of Self-Supervised Models for Speech Emotion Recognition
Wu, Y., Yue, P., Cheng, C., & Li, T. (2023) · Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC) · doi:10.1109/apsipaasc58517.2023.10317508 · Cited by 5
Yue, X., Gao, X., Qian, X., & Li, H. (2024) · Electronics · doi:10.3390/electronics13010190 · Cited by 5
Acoustic BPE for Speech Generation with Discrete Tokens
Shen, F., Guo, Y., Du, C., Chen, X., & Yu, K. (2024) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp48485.2024.10446063 · Cited by 11
State-of-the-Art Review on Recent Trends in Automatic Speech Recognition
Kandji, A. K., Ba, C., & Ndiaye, S. (2024) · Lecture notes of the Institute for Computer Sciences, Social Informatics and Telecommunications Engineering · doi:10.1007/978-3-031-63999-9_11 · Cited by 5
Converting Anyone's Voice: End-to-End Expressive Voice Conversion with A Conditional Diffusion Model
Du, Z., Lu, J., Zhou, K., Kaushik, L., & Şişman, B. (2024) · The Speaker and Language Recognition Workshop (Odyssey) · doi:10.21437/odyssey.2024-25 · Cited by 7
Transfer learning for crash design
Colella, G., Lange, V. A., & Duddeck, F. M. E. (2024) · Discover Mechanical Engineering · doi:10.1007/s44245-024-00059-2 · Cited by 6
StethoSpeech: Speech Generation Through a Clinical Stethoscope Attached to the Skin
Shah, N., Sahipjohn, N., Tambrahalli, V., Subramanian, R., & Gandhi, V. (2024) · Proceedings of the ACM on Interactive Mobile Wearable and Ubiquitous Technologies · doi:10.1145/3678515 · Cited by 5
Versatile Multimodal Controls for Expressive Talking Human Animation
Qin, Z., Zheng, R., Wang, Y., Li, T., Zhu, Z., Zhou, S., Yang, M., & Wang, L. (2025) · ACM International Conference on Multimedia (ACM MM) · doi:10.1145/3746027.3755401 · Cited by 9
A fine-tuning approach research of pre-trained model with two stage
Zhang, L., & Hu, Y. (2021) · 2021 IEEE International Conference on Power Electronics, Computer Applications (ICPECA) · doi:10.1109/icpeca51329.2021.9362566 · Cited by 6
Improving Pseudo-Label Training For End-To-End Speech Recognition Using Gradient Mask
Ling, S., Shen, C., Cai, M., & Ma, Z. (2022) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp43922.2022.9746249 · Cited by 6
de Velasco, M., Justo, R., & Torres, M. I. (2022) · Applied Sciences · doi:10.3390/app12041902 · Cited by 5
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
