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 701–800 of 1,003
Self-Supervised Speaker Recognition Training using Human-Machine Dialogues
Cekic, M., Li, R., Chen, Z., Yang, Y., Stolcke, A., & Madhow, U. (2022) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp43922.2022.9747325 · Cited by 5
Multi-Feature Integration for Speaker Embedding Extraction
Sankala, S., Shaik Mohammad Rafi, B., & Murty, K. S. R. (2022) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp43922.2022.9746318 · Cited by 5
Toward Low-Cost End-to-End Spoken Language Understanding
Dinarelli, M., Naguib, M., & Portet, F. (2022) · Interspeech (USB) · doi:10.21437/interspeech.2022-10702 · Cited by 5
A Light CNN with Split Batch Normalization for Spoofed Speech Detection Using Data Augmentation
Lin, H.-J., Ai, Y., & Ling, Z.-H. (2022) · Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC) · doi:10.23919/apsipaasc55919.2022.9980260 · Cited by 5
A Comparison Between Convolutional and Transformer Architectures for Speech Emotion Recognition
Iyer, S., Glackin, C., Cannings, N., Veneziano, V., & Sun, Y. (2022) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn55064.2022.9891882 · Cited by 5
Predicting Multi-Codebook Vector Quantization Indexes for Knowledge Distillation
Guo, L., Yang, X., Wang, Q., Kong, Y., Yao, Z., Cui, F., Kuang, F., Kang, W., Lin, L., Luo, M., et al. (2023) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp49357.2023.10095268 · Cited by 6
Unsupervised and Semi-Supervised Speech Recognition System: A Review
Al-Irhayim, Y. F., & Al-Zakarya, M. (2023) · Maǧallaẗ al-rāfidayn li-ʿulūm al-ḥāsibāt wa-al-riyāḍiyyāẗ/Al-Rafidain journal for computer sciences and mathematics · doi:10.33899/csmj.2023.179466 · Cited by 5
Self-Supervised Learning Representations for Dialect Identification with Sparse Transformers
Shen, R., Li, Y., Gu, H., Wang, Y. H., Huang, J., & She, Q. (2024) · International Conference on Control Engineering and Artificial Intelligence (CCEAI) · doi:10.1145/3640824.3640825 · Cited by 5
Language Recognition Based on Unsupervised Pretrained Models
Yu, H., Zhao, J., Yang, S., Wu, Z., Nie, Y., & Zhang, W.-Q. (2021) · Interspeech (USB) · doi:10.21437/interspeech.2021-807 · Cited by 5
Gimeno, P., Ortega, A., Miguel, A., & Lleida, E. (2021) · Interspeech (USB) · doi:10.21437/interspeech.2021-309 · Cited by 5
Abdullah, B., Zaitova, I., Avgustinova, T., Möbius, B., & Klakow, D. (2021) · BlackboxNLP Workshop on Analyzing and Interpreting Neural Networks for NLP (BlackboxNLP) · doi:10.18653/v1/2021.blackboxnlp-1.32 · Cited by 5
Multimodal Fusion Strategies for Physiological-emotion Analysis
Zhang, T., Huang, Z., Li, R., Zhao, J., & Jin, Q. (2021) · doi:10.1145/3475957.3484452 · Cited by 5
Audio MFCC-gram Transformers for respiratory insufficiency detection in COVID-19
Gauy, M. M., & Finger, M. (2021) · Simpósio Brasileiro de Tecnologia da Informação e da Linguagem Humana (STIL) · doi:10.5753/stil.2021.17793 · Cited by 5
Curriculum Optimization for Low-Resource Speech Recognition
Kuznetsova, A., Kumar, A. K., Drexler, J., & Tyers, F. M. (2022) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp43922.2022.9746674 · Cited by 5
Improved Representation Learning For Acoustic Event Classification Using Tree-Structured Ontology
Zharmagambetov, A. S., Tang, Q., Kao, C.-C., Zhang, Q., Sun, M., Rozgić, V., Droppo, J., & Wang, C. (2022) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp43922.2022.9746266 · Cited by 5
Fooling the Forgers: A Multi-Stage Framework for Audio Deepfake Detection
Kashyap, G. S., Siddiqui, Z. H., Azeez, M. A., Ali, R., Kumar, S., Kamuni, N., & Gao, J. (2025) · ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) · doi:10.1109/icassp49660.2025.10888175 · Cited by 4
Lindsey, M., Robinson, N. R., Kubala, F., & Stern, R. M. (2023) · IEEE Workshop on Automatic Speech Recognition and Understanding (ASRU) · doi:10.1109/asru57964.2023.10389626 · Cited by 4
WhisPAr: Transferring pre-trained audio models to fine-grained classification via Prompt and Adapter
Shi, B., Wang, H., Lu, C., & Zhao, M. (2024) · Knowledge-Based Systems · doi:10.1016/j.knosys.2024.112242 · Cited by 4
Enhancing analysis of diadochokinetic speech using deep neural networks
Segal, Y., Hitczenko, K., Goldrick, M., Buchwald, A. B., Roberts, A., & Keshet, J. (2024) · Computer Speech & Language · doi:10.1016/j.csl.2024.101715 · Cited by 4
Long-term self-supervised learning for accelerometer-based sleep–wake recognition
Logacjov, A., Bach, K., & Mork, P. J. (2024) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2024.109758 · Cited by 5
Innovative Learning Assistance Through the Multiverse AI Educator Using Natural Language Processing
Leelavathy, N., Sujatha, B., Sindhu, B., Manikanti, Y. D., Geethanjali, P., Kumar, K. R., & Prabhu, K. (2024) · Indian Journal of Science and Technology · doi:10.17485/ijst/v17i47.3789 · Cited by 4
Bimodal Sentiment Analysis Based on a Pre-Trained Model and Masked Attention Fusion
Cai, L., Li, H., Zhang, N., & He, J. (2025) · IEEE Transactions on Audio Speech and Language Processing · doi:10.1109/taslpro.2025.3564826 · Cited by 4
Zuo, L., & Mak, M. (2025) · IEEE Journal of Biomedical and Health Informatics · doi:10.1109/jbhi.2025.3566767 · Cited by 4
Transcription for Thai Traditional Medicine Texts with Wav2Vec2
Popun, J., Lee, W., Prayote, A., Srisomboon, K., & Pipanmekaporn, L. (2025) · International Electrical Engineering Congress (iEECON) · doi:10.1109/ieecon64081.2025.10987706 · Cited by 4
Is self-supervised learning enough to fill in the gap? A study on speech inpainting
Asaad, I., Jacquelin, M., Perrotin, O., Laurent Girin, B., & Hueber, T. (2025) · Computer Speech & Language · doi:10.1016/j.csl.2025.101922 · Cited by 4
Frequency-aware experts with multi-stage fusion for multimodal sentiment analysis
Zhu, X., & Li, Y. (2025) · Journal of Intelligent Information Systems · doi:10.1007/s10844-025-01006-7 · Cited by 4
Machine Learning for the Complex, Multi-scale Datasets in Fusion Energy
Churchill, R. M., Choi, J. Y., Kube, R., Chang, C. S., & Klasky, S. (2020) · Communications in computer and information science · doi:10.1007/978-3-030-63393-6_18 · Cited by 4
Towards Robust Waveform-Based Acoustic Models
Oglić, D., Cvetković, Z., Peter Sollich, A., Renals, S. J., & Yu, B. (2022) · IEEE/ACM Transactions on Audio Speech and Language Processing · doi:10.1109/taslp.2022.3172632 · Cited by 4
Speech Emotion Recognition Based on Deep Learning
Liu, M., Ke, Y., Zhang, Y., Shao, W., & Song, L. (2022) · IEEE Region 10 Conference (TENCON) · doi:10.1109/tencon55691.2022.9978156 · Cited by 4
On‐device audio‐visual multi‐person wake word spotting
Li, Y., Wang, G., Chen, Z., Tang, H., & Liu, H. (2023) · CAAI Transactions on Intelligence Technology · doi:10.1049/cit2.12189 · Cited by 4
Efficient Utilization of Large Pre-Trained Models for Low Resource ASR
Vieting, P., Lüscher, C., Dierkes, J., Schlüter, R., & Ney, H. (2023) · IEEE International Conference on Acoustics, Speech, and Signal Processing Workshops (ICASSPW) · doi:10.1109/icasspw59220.2023.10193570 · Cited by 4
Avram, A.-M., Smădu, R.-A., Păiș, V., Cercel, D.-C., Ion, R., & Tufis, D. I. (2023) · International Conference on Telecommunications and Signal Processing (TSP) · doi:10.1109/tsp59544.2023.10197791 · Cited by 4
Lee, J.-H., & Chang, J. (2023) · IEEE/ACM Transactions on Audio Speech and Language Processing · doi:10.1109/taslp.2023.3343615 · Cited by 4
Ding, S., Qiu, D., Rim, D., He, Y., Rybakov, O., Li, B., Prabhavalkar, R., Wang, W., Sainath, T. N., Han, Z., et al. (2024) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp48485.2024.10448217 · Cited by 4
Accurate Semi-supervised Automatic Speech Recognition via Multi-hypotheses-Based Curriculum Learning
Kim, J., Park, K. H., & Kang, U. (2024) · Lecture notes in computer science · doi:10.1007/978-981-97-2262-4_4 · Cited by 4
Beyond Labels: A Comprehensive Review of Self-Supervised Learning and Intrinsic Data Properties
Zhu, Y. (2023) · Journal of Science & Technology · doi:10.55662/jst.2023.4403 · Cited by 4
Maoheng, L. (2024) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn60899.2024.10650481 · Cited by 4
Knowledge-guided EEG Representation Learning
Kommineni, A., Avramidis, K., Leahy, R. M., & Narayanan, S. S. (2024) · Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC) · doi:10.1109/embc53108.2024.10782310 · Cited by 4
Comprehensive Benchmarking and Analysis of Open Pretrained Thai Speech Recognition Models
Tipakasorn, P., Chatthong, O., Yonehana, R., & Thangthai, K. (2024) · International Conference on Speech Database and Assessments · doi:10.1109/o-cocosda64382.2024.10800399 · Cited by 4
Multi-Head Attention-Enhanced Speech Recognition for Reduced Data Requirements
Li, Y., Zhou, Y., Qiu, Z., Wang, Y., Wang, J., & Huang, G. (2024) · Electronics · doi:10.3390/electronics14010128 · Cited by 4
Chen, Z., Song, C., Chen, Y., Li, J., Fu, G., Tong, Y., & Zhao, Q. Y. (2024) · Conference proceedings/Conference proceedings - IEEE International Conference on Systems, Man, and Cybernetics · doi:10.1109/smc54092.2024.10831967 · Cited by 4
Fault diagnosis of batch processes for small samples based on contrastive learning
Xu, J., Yao, Z., & Jiang, Q. (2025) · The Canadian Journal of Chemical Engineering · doi:10.1002/cjce.25651 · Cited by 4
Naeeni, N., & Nasersharif, B. (2025) · Computers in Biology and Medicine · doi:10.1016/j.compbiomed.2025.110510 · Cited by 4
On Scaling Contrastive Representations for Low-Resource Speech Recognition
Borgholt, L., Tax, T. M. S., Havtorn, J. D., Maaløe, L., & Igel, C. (2021) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp39728.2021.9414310 · Cited by 4
A Self-Supervised Model for Language Identification Integrating Phonological Knowledge
Zhan, Q., Xie, X., Hu, C., & Cheng, H. (2021) · Electronics · doi:10.3390/electronics10182259 · Cited by 4
Semi-supervised Deep Learning for Stress Prediction: A Review and Novel Solutions
Alshamrani, M. I. (2021) · International Journal of Advanced Computer Science and Applications · doi:10.14569/ijacsa.2021.0120949 · Cited by 4
Liu, Z., Kang, X., & Ren, F. (2022) · IFIP advances in information and communication technology · doi:10.1007/978-3-031-03948-5_28 · Cited by 4
Low-Resource Speech Recognition Based on Transfer Learning
Tsai, W.-H., Le, P. T., Tai, T.-C., Huang, C.-L., & Wang, J. (2022) · RIVF International Conference on Computing and Communication Technologies (RIVF) · doi:10.1109/rivf55975.2022.10013881 · Cited by 4
Direct enhancement of pre-trained speech embeddings for speech processing in noisy conditions
Ali, M. N., Brutti, A., & Falavigna, D. (2023) · Computer Speech & Language · doi:10.1016/j.csl.2023.101501 · Cited by 4
Do Coarser Units Benefit Cluster Prediction-Based Speech Pre-Training?
Elkahky, A. M., Hsu, W.-N., Tomasello, P., Nguyen, T. A., Algayres, R., Adi, Y., Copet, J., Emmanuel Dupoux, A., & Mohamed, A. (2023) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp49357.2023.10096788 · Cited by 7
Huang, Z., Chen, Z., Kanda, N., Wu, J., Wang, Y., Li, J., Yoshioka, T., Wang, X., & Wang, P. (2023) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp49357.2023.10094787 · Cited by 4
Resource-Efficient Transfer Learning from Speech Foundation Model Using Hierarchical Feature Fusion
Huo, Z., Sim, K. C., Li, B., Hwang, D., Sainath, T. N., & Strohman, T. (2023) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp49357.2023.10096799 · Cited by 5
Udupa, S., Siddarth, C., & Ghosh, P. (2023) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp49357.2023.10094703 · Cited by 4
Introducing Semantics into Speech Encoders
Xu, D. C., Dong, S., Wang, C., Kim, S., Lin, Z., Liu, B., Shrivastava, A., Li, S.-W. D., Tseng, L.-H., Lin, G.-T., et al. (2023) · Proceedings of the conference - Association for Computational Linguistics. Meeting · doi:10.18653/v1/2023.acl-long.639 · Cited by 7
Self-citationSpeechNet: Weakly Supervised, End-to-End Speech Recognition at Industrial Scale
Tang, R., Kumar, K., Yang, G., Pandey, A., Mao, Y., Belyaev, V., Emmadi, M., Murray, C., Türe, F., & Lin, J. (2022) · Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.18653/v1/2022.emnlp-industry.29 · Cited by 4
Huang, W., Zong, Y., Shi, Z., & Liu, P. (2023) · IEEE Symposium on Computers and Communications (ISCC) · doi:10.1109/iscc58397.2023.10218074 · Cited by 4
Generating Synthetic Speech from SpokenVocab for Speech Translation
Zhao, J., Haffari, G., & Shareghi, E. (2023) · Findings of the Association for Computational Linguistics: EACL · doi:10.18653/v1/2023.findings-eacl.147 · Cited by 4
ASR for Indian Regional Languages Using Fine-Tuned Wav2Vec2 Model
Ghadekar, P. P., Jhanwar, K., Karpe, A., Sivanandan, A., Shetty, T., & Khushalani, P. (2023) · Lecture notes in electrical engineering · doi:10.1007/978-981-99-3656-4_14 · Cited by 4
Wang, Z., Xu, X., Li, X., Li, H., Wei, X., & Huang, D. (2023) · Applied Sciences · doi:10.3390/app132011249 · Cited by 4
Exploring the Impact of Different Approaches for Spoken Dialect Identification of Konkani Language
Monteiro, S., Angra, A., Muralikrishna, H., Thenkanidiyoor, V., & Dileep, A. D. (2023) · Lecture notes in computer science · doi:10.1007/978-3-031-48312-7_37 · Cited by 4
GR0: Self-Supervised Global Representation Learning for Zero-Shot Voice Conversion
Wang, Y., Su, J., Finkelstein, A., & Jin, Z. (2024) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp48485.2024.10448232 · Cited by 4
MERSA: Multimodal Emotion Recognition with Self-Align Embedding
Le, Q. B., Trinh, K., Son, N. D. H., Tran, P.-N., Nguyen, C. T., & Dang, D. N. M. (2024) · International Conference on Information Networking · doi:10.1109/icoin59985.2024.10572116 · Cited by 4
On the Transferability of Large-Scale Self-Supervision to Few-Shot Audio Classification
Heggan, C., Budgett, S., Hospedales, T., & Yaghoobi, M. (2024) · IEEE International Conference on Acoustics, Speech, and Signal Processing Workshops (ICASSPW) · doi:10.1109/icasspw62465.2024.10626094 · Cited by 4
Ferdiansyah, D., & Aditya, C. S. K. (2024) · Jurnal Teknik Elektro dan Komputer TRIAC · doi:10.21107/triac.v11i1.24332 · Cited by 4
Wav2SQL: Direct Generalizable Speech-To-SQL Parsing
Liu, H., Huang, R., He, J., Sun, G., Shen, R., Cheng, X., & Zhao, Z. (2024) · Findings of the Association for Computational Linguistics: ACL (Findings of ACL) · doi:10.18653/v1/2024.findings-acl.251 · Cited by 4
SEQ-CPC : Sequential Contrastive Predictive Coding for Automatic Speech Recognition
Chen, Y., Zhao, J., Wang, W., Fang, M., Kang, H., Wang, L., Wei, T., Ma, J., Wang, S., & Xiao, J. Z. (2021) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp39728.2021.9413645 · Cited by 4
Audio DistilBERT: A Distilled Audio BERT for Speech Representation Learning
Yu, F., Guo, J., Xi, W., Yang, Z., Jiang, R., & Zhang, C. (2021) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn52387.2021.9533328 · Cited by 4
Cross-Domain Semi-Supervised Audio Event Classification Using Contrastive Regularization
Lee, D., & Lee, K. (2021) · IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA) · doi:10.1109/waspaa52581.2021.9632721 · Cited by 4
Guimarães, H. R., Beccaro, W., & Ramírez, M. A. (2021) · Machine learning for signal processing ... · doi:10.1109/mlsp52302.2021.9596103 · Cited by 4
Towards A Common Speech Analysis Engine
Aronowitz, H., Gat, I., Morais, E. D. S., Zhu, W., & Hoory, R. (2022) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp43922.2022.9747756 · Cited by 4
Quantifying Language Variation Acoustically with Few Resources
Bartelds, M., & Wieling, M. B. (2022) · Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL-HLT) · doi:10.18653/v1/2022.naacl-main.273 · Cited by 4
Hi,KIA: A Speech Emotion Recognition Dataset for Wake-Up Words
Kim, T., Doh, S., Lee, G., Jeon, H., Nam, J., & Suk, H. (2022) · Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC) · doi:10.23919/apsipaasc55919.2022.9980227 · Cited by 4
Fine-grained Early Frequency Attention for Deep Speaker Recognition
Hajavi, A., & Etemad, A. (2022) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn55064.2022.9892054 · Cited by 4
Li, J., Mak, M., Yan, N., & Wang, L. (2023) · Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC) · doi:10.1109/apsipaasc58517.2023.10317476 · Cited by 3
Speech-Based Screening of Multiple Sclerosis By Features Derived from Self-Supervised Models
Gosztolya, G., & Egas-López, J. V. (2023) · International Conference on Electrical, Computer and Energy Technologies (ICECET) · doi:10.1109/icecet58911.2023.10389218 · Cited by 3
Secured Encrypted Morse Code Communication using Fernet in Defense Applications
Meena, R. D., Pandiyarajan, P., Narasimha, D. L., Yadav, G. V. K., Poornesh, J., & Reddy, C. S. K. (2024) · IEEE Pune Section International Conference (PuneCon) · doi:10.1109/punecon63413.2024.10895802 · Cited by 3
Integrated Word2Vec-Based Speech Annotations for Enhanced EEG Decoding of Speech Intentions
Jang, S.-N., Park, H.-Y., Kim, S.-W., Yu, S.-H., Lee, M., & Jeong, J.-H. (2025) · International Winter Conference on Brain-Computer Interface (BCI) · doi:10.1109/bci65088.2025.10931508 · Cited by 3
Chen, H., Wang, C., Wang, Q., Du, J., Siniscalchi, S. M., Wan, G., Pan, J., & Ding, H. (2025) · Information Fusion · doi:10.1016/j.inffus.2025.103218 · Cited by 3
Zahid, S. M., & Qazi, S. A. (2025) · IEEE Access · doi:10.1109/access.2025.3569579 · Cited by 4
OpenBEATs: A Fully Open-Source General-Purpose Audio Encoder
Bharadwaj, S., Cornell, S., Choi, K., Fukayama, S., Shim, H.-J., Deshmukh, S., & Watanabe, S. (2025) · IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA) · doi:10.1109/waspaa66052.2025.11230965 · Cited by 3
Peters, J., Mora, K., Mahecha, M. D., Ji, C., Montero, D., Mosig, C., & Kraemer, G. (2026) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2026.3707966 · Cited by 5
WhisMultiNet: Advancing End-to-End Speech Topic Classification With Whisper and MultiGateGNN
Qi, X., Zhao, X., Li, Z., & He, L. (2025) · IEEE Transactions on Audio Speech and Language Processing · doi:10.1109/taslpro.2025.3622978 · Cited by 3
Beşirli, A., Karakadıoğlu, T., & Demiroğlu, C. (2025) · EURASIP Journal on Audio Speech and Music Processing · doi:10.1186/s13636-025-00439-w · Cited by 3
Towards Multi-Brain Decoding in Autism: A Self-Supervised Learning Approach
Ranjbaran, G., Moreau, Q., Dubois, A. E. E., & Dumas, G. (2026) · Neuroinformatics · doi:10.1007/s12021-025-09755-0 · Cited by 3
A deep neural network-based automatic mispronunciation detection in Bengali accented English speech
Bharati, P., Chandra, S., Aitawade, A., Pramanik, D., Gaddamedi, S. P., & Mandal, S. K. D. (2026) · Discover Computing · doi:10.1007/s10791-026-09959-1 · Cited by 3
Variational Low-Rank Adaptation for Personalized Impaired Speech Recognition
Pokel, N., Moure, P., Boehringer, R., Liu, S., & Gao, Y. (2026) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp55912.2026.11462593 · Cited by 6
An Empirical Study on Speech Restoration Guided by Self-Supervised Speech Representation
Byun, J., Ji, Y., Chung, S.-W., Choe, S., & Choi, M.-S. (2023) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp49357.2023.10095881 · Cited by 3
Wav2vec‐MoE: An unsupervised pre‐training and adaptation method for multi‐accent ASR
Lin, Y., Zhang, S., Gao, Z., Wang, L., Yang, Y., & Dang, J. (2023) · Electronics Letters · doi:10.1049/ell2.12823 · Cited by 3
Xiang, Y., Yang, Y., Sun, J., Guo, Y., & Bai, H. (2023) · International Conference on Artificial Intelligence and Blockchain Technology (AIBT) · doi:10.1109/aibt57480.2023.00025 · Cited by 3
Dual Contrastive Learning for Self-Supervised ECG Mapping to Emotions and Glucose Levels
Lalzary, N., & Wolf, L. (2023) · Proceedings of IEEE Sensors/Proceedings of IEEE Sensors ... · doi:10.1109/sensors56945.2023.10325116 · Cited by 3
Yolwas, N., Sun, L., Li, X., Liu, Q., & Wang, Z. (2024) · Journal of Shanghai Jiaotong University (Science) · doi:10.1007/s12204-024-2738-8 · Cited by 3
Semantic Communications - A Comprehensive Survey for Future Research Issues
Lee, S., & Lee, Y. H. (2024) · International Conference on Ubiquitous and Future Networks · doi:10.1109/icufn61752.2024.10625026 · Cited by 5
Disentanglement of Prosody Representations via Diffusion Models and Scheduled Gradient Reversal
Qu, L., Weber, C., Wang, W., Jin, J., Gao, Y., Li, T., & Wermter, S. (2025) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2025.3534822 · Cited by 4
Progressive Residual Extraction Based Pre-Training for Speech Representation Learning
Wang, T., Li, J., Ma, Z., Cao, R., Chen, X., Wang, L., Ge, M., Wang, X., Wang, Y. G., Dang, J., et al. (2025) · IEEE Transactions on Audio Speech and Language Processing · doi:10.1109/taslpro.2025.3564118 · Cited by 3
Chen, C., & Huang, L. (2025) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2025.111439 · Cited by 4
Low-Power Learnable Digital Audio Feature Extractor for Always-on Keyword Spotting in Edge Devices
Shen, C., Hu, J., Goh, W. L., Chong, Y. S., Do, A. T., & Gao, Y. (2025) · IEEE Transactions on Circuits and Systems I Regular Papers · doi:10.1109/tcsi.2025.3594961 · Cited by 3
Generative AI for Short Sound Message Transmission in the Internet of Things
Favero, M., Buratto, A., Badia, L., Canazza, S., & Murrone, L. (2025) · IEEE International Conference on Machine Learning for Communication and Networking (ICMLCN) · doi:10.1109/icmlcn64995.2025.11140271 · Cited by 3
Self-supervised Graph Representation Learning with Variational Inference
Liao, Z., Liang, W., Liu, H., Mu, J., & Zhang, X. (2021) · Lecture notes in computer science · doi:10.1007/978-3-030-75768-7_10 · Cited by 3
Voice Activation for Low-Resource Languages
Kolesau, A., & Šešok, D. (2021) · Applied Sciences · doi:10.3390/app11146298 · Cited by 3
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
