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 501–600 of 1,003
Kim, J., Kumar, M., Gowda, D., Garg, A., & Kim, C. (2021) · IEEE Workshop on Automatic Speech Recognition and Understanding (ASRU) · doi:10.1109/asru51503.2021.9688019 · Cited by 10
Maestro-U: Leveraging Joint Speech-Text Representation Learning for Zero Supervised Speech ASR
Chen, Z., Bapna, A., Rosenberg, A., Zhang, Y., Ramabhadran, B., Moreno, P. J., & Chen, N. (2023) · IEEE Spoken Language Technology Workshop (SLT) · doi:10.1109/slt54892.2023.10022791 · Cited by 10
Improving Few-Shot Learning for Talking Face System with TTS Data Augmentation
Chen, Q., Ma, Z., Liu, T., Tan, X., Lu, Q., Yu, K., & Chen, X. (2023) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp49357.2023.10094777 · Cited by 10
Efficient Adapter Tuning of Pre-Trained Speech Models for Automatic Speaker Verification
Sang, M., & Hansen, J. H. L. (2024) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp48485.2024.10446686 · Cited by 12
DQ-Whisper: Joint Distillation and Quantization for Efficient Multilingual Speech Recognition
Shao, H., Liu, B., Wang, W., Gong, X., & Qian, Y. (2024) · IEEE Spoken Language Technology Workshop (SLT) · doi:10.1109/slt61566.2024.10832149 · Cited by 18
SoccerNet-Echoes: A Soccer Game Audio Commentary Dataset
Gautam, S., Sarkhoosh, M. H., Held, J., Midoglu, C., Cioppa, A., Giancola, S., Thambawita, V. L., Riegler, M., Halvorsen, P., & Shah, M. A. (2024) · International Symposium on Multimedia · doi:10.1109/ism63611.2024.00016 · Cited by 10
Lattice-Free Mmi Adaptation of Self-Supervised Pretrained Acoustic Models
Vyas, A., Madikeri, S. R., & Bourlard, H. A. (2021) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp39728.2021.9414741 · Cited by 10
Gamayun - Language Technology for Humanitarian Response
Öktem, A., Jaam, M. A., DeLuca, E., & Tang, G. (2020) · IEEE Global Humanitarian Technology Conference (GHTC) · doi:10.1109/ghtc46280.2020.9342939 · Cited by 10
Unsupervised Data Selection for Speech Recognition with Contrastive Loss Ratios
Park, C., Ahmad, R., & Hain, T. (2022) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp43922.2022.9747390 · Cited by 10
A Systematic Comparison of Phonetic Aware Techniques for Speech Enhancement
Tal, O., Mandel, M., Kreuk, F., & Adi, Y. (2022) · Interspeech (USB) · doi:10.21437/interspeech.2022-695 · Cited by 10
Shen, Y., Liu, Q., Fan, Z., Liu, J., & Wumaier, A. (2022) · IEEE Access · doi:10.1109/access.2022.3212417 · Cited by 11
Speech Recognition for Air Traffic Control via Feature Learning and End-to-End Training
Peng, F. A. N., Hua, X., Lin, Y., Yang, B., ZHANG, J., Ge, W., & Guo, D. (2023) · IEICE Transactions on Information and Systems · doi:10.1587/transinf.2022edp7151 · Cited by 10
Comparison of Deep Learning Methods for Spoken Language Identification
Korkut, C., Haznedaroğlu, A., & Arslan, L. M. (2020) · Lecture notes in computer science · doi:10.1007/978-3-030-60276-5_23 · Cited by 10
A Brief Overview of Unsupervised Neural Speech Representation LearningPreprint
Borgholt, L., Havtorn, J. D., Edin, J., Maaløe, L., & Igel, C. (2022) · arXiv (Cornell University) · doi:10.48550/arxiv.2203.01829 · Cited by 15
Kim, M., & Jang, G. (2024) · Applied Sciences · doi:10.3390/app14188138 · Cited by 10
Deep network compression with teacher latent subspace learning and LASSO
Oyedotun, O. K., Shabayek, A. E. R., Aouada, D., & Ottersten, B. (2020) · Applied Intelligence · doi:10.1007/s10489-020-01858-2 · Cited by 9
Phonetically Motivated Self-Supervised Speech Representation Learning
Yue, X., & Li, H. (2021) · Interspeech (USB) · doi:10.21437/interspeech.2021-905 · Cited by 9
Stabilizing Label Assignment for Speech Separation by Self-Supervised Pre-Training
Huang, S.-F., Chuang, S.-P., Liu, D.-R., Chen, Y., Yang, G.-P., & Lee, H.-Y. (2021) · Interspeech (USB) · doi:10.21437/interspeech.2021-763 · Cited by 11
Automatic Behavior Assessment from Uncontrolled Everyday Audio Recordings by Deep Learning
Schindler, D., Spors, S., Demiray, B., & Krüger, F. (2022) · Sensors · doi:10.3390/s22228617 · Cited by 10
A Unified One-Shot Prosody and Speaker Conversion System with Self-Supervised Discrete Speech Units
Chen, L., Watanabe, S., & Rudnicky, A. I. (2023) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp49357.2023.10095565 · Cited by 9
Oota, S. R., Pahwa, K., Marreddy, M., Gupta, M., & Bapi, R. S. (2023) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp49357.2023.10096248 · Cited by 10
An Adapter Based Multi-Label Pre-Training for Speech Separation and Enhancement
Wang, T., Chen, X., Chen, Z., Yu, S., & Zhu, W. (2023) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp49357.2023.10094883 · Cited by 11
Cocktail Hubert: Generalized Self-Supervised Pre-Training for Mixture and Single-Source Speech
Fazel-Zarandi, M., & Hsu, W.-N. (2023) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp49357.2023.10096630 · Cited by 12
Self-Supervised Audio Encoder with Contrastive Pretraining for Respiratory Anomaly Detection
Kulkarni, S., Watanabe, H., & Homma, F. (2023) · IEEE International Conference on Acoustics, Speech, and Signal Processing Workshops (ICASSPW) · doi:10.1109/icasspw59220.2023.10193030 · Cited by 9
Mehra, S., Ranga, V., Agarwal, R., & Susan, S. (2024) · Multimedia Tools and Applications · doi:10.1007/s11042-024-18804-w · Cited by 9
Noise-Robust Multilingual Speech Recognition and the Tatar Speech Corpus
Mussakhojayeva, S., Абрекович, Г. Р., Эрнстович, Х. Б., Galimov, M., Orel, D., Abilbekov, A., & Varol, H. A. (2024) · International Conference on Artificial Intelligence in Information and Communication (ICAIIC) · doi:10.1109/icaiic60209.2024.10463419 · Cited by 9
Bi-Modal Bi-Task Emotion Recognition Based on Transformer Architecture
Song, Y., & Zhou, Q. (2024) · Applied Artificial Intelligence · doi:10.1080/08839514.2024.2356992 · Cited by 9
Bargum, A. R., Serafin, S., & Erkut, C. (2024) · Frontiers in Signal Processing · doi:10.3389/frsip.2024.1339159 · Cited by 13
Securing Wireless Networks Against Emerging Threats: An Overview of Protocols and Solutions
Lakhani, R., & Sachan, R. C. (2024) · Journal of Science & Technology · doi:10.55662/jst.2024.5406 · Cited by 9
Ravi, V., Fan, R., Afshan, A., Lu, H., & Alwan, A. A. (2020) · Interspeech (USB) · doi:10.21437/interspeech.2020-2957 · Cited by 9
A Comparison of Discrete Latent Variable Models for Speech Representation Learning
Zhou, H., Baevski, A., & Auli, M. (2021) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp39728.2021.9413680 · Cited by 10
Self-citationCrossmodal Clustered Contrastive Learning: Grounding of Spoken Language to Gesture
Lee, D. W., Ahuja, C., & Morency, L. (2021) · Companion Publication of the International Conference on Multimodal Interaction (ICMI Companion) · doi:10.1145/3461615.3485408 · Cited by 9
Chen, L., Xu, C., Zhang, X., Ren, X., Zheng, X., Zhang, C., Guo, L., & Yu, B. (2022) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp43922.2022.9746981 · Cited by 9
Self-supervised Representation Learning for Speech Processing
Lee, H.-Y., Mohamed, A., Watanabe, S., Sainath, T. N., Livescu, K., Li, S.-W. D., Yang, S.-W., & Kirchhoff, K. (2022) · doi:10.18653/v1/2022.naacl-tutorials.2 · Cited by 9
Improving Speech Emotion Recognition via Fine-tuning ASR with Speaker Information
Thang, T. B., Nguyễn, T. L., Dang, D. S., Le, N. M., & Hai, V. (2022) · Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC) · doi:10.23919/apsipaasc55919.2022.9980214 · Cited by 9
Augmentation Invariant Discrete Representation for Generative Spoken Language Modeling
Gat, I., Kreuk, F., Nguyen, T. A., Lee, A., Copet, J., Synnaeve, G., Emmanuel Dupoux, A., & Adi, Y. (2023) · International Conference on Spoken Language Translation (IWSLT) · doi:10.18653/v1/2023.iwslt-1.46 · Cited by 9
Design and tool flow of a reconfigurable asynchronous neural network accelerator
Zhang, J., Wu, H., Chen, W., Wei, S., & Chen, H. (2021) · Tsinghua Science & Technology · doi:10.26599/tst.2020.9010048 · Cited by 9
CSTNet: Contrastive Speech Translation Network for Self-Supervised Speech Representation LearningPreprint
Khurana, S., Laurent, A., & Glass, J. R. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2006.02814 · Cited by 11
Representation Learning for Sequence Data with Deep Autoencoding Predictive ComponentsPreprint
Bai, J., Wang, W., Zhou, Y., & Xiong, C. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2010.03135 · Cited by 13
Wang, C., Wu, Y., Liu, S., Li, J., Qian, Y., Kumatani, K., & Wei, F. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2107.05233 · Cited by 14
Qin, X., Li, M., Bu, H., Narayanan, S. S., & Li, H. (2022) · doi:10.21437/ffsvc.2022-3 · Cited by 8
RawSpectrogram: On the Way to Effective Streaming Speech Anti-Spoofing
Grinberg, P., & Shikhov, V. (2023) · IEEE Access · doi:10.1109/access.2023.3321919 · Cited by 8
Leveraging Self-Supervised Speech Representations for Domain Adaptation in Speech Enhancement
Lee, C.-H., Yang, C. J., Srinivasa, R. S., Saidutta, Y. M., Cho, J., Shen, Y., & Jin, H. (2024) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp48485.2024.10447573 · Cited by 8
SSMIM: Semi-supervised Multimodal Interaction Model for real-time conversational emotion recognition
Liu, H., & Zhong, K. (2025) · The Journal of Supercomputing · doi:10.1007/s11227-025-07373-w · Cited by 9
Semantic and Technical Noise Modeling in Semantic Image Communication Over Wireless Channels
Samarathunga, P., Pollwaththage, N., Fernando, T., Jayasinghe, U., Ihalagamage, N., Ganearachchi, Y., & Fernando, A. (2025) · IEEE Access · doi:10.1109/access.2025.3600320 · Cited by 10
Aligning Speech-Text Representations via Contrastive Modality Translation
Chien, J., & Liu, P.-Y. (2025) · IEEE Transactions on Audio Speech and Language Processing · doi:10.1109/taslpro.2025.3603910 · Cited by 8
Representation Potentials of Foundation Models for Multimodal Alignment: A Survey
Lu, J., Wang, H., Xu, Y., Wang, Y., Yang, K., & Fu, Y. (2025) · Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.18653/v1/2025.emnlp-main.843 · Cited by 14
Do End-to-End Speech Recognition Models Care About Context?
Borgholt, L., Havtorn, J. D., Agić, Ż., Søgaard, A., Maaløe, L., & Igel, C. (2020) · Interspeech (USB) · doi:10.21437/interspeech.2020-1750 · Cited by 10
Kim, J.-W., Yoon, H., & Jung, H. (2021) · IEEE Access · doi:10.1109/access.2021.3115608 · Cited by 8
Connecting the Dots in Self-Supervised Learning: A Brief Survey for Beginners
Fang, P., Li, X., Yang, Y., Zhang, S., Kang, Q.-Y., Li, X., & Lan, Z. (2022) · Journal of Computer Science and Technology · doi:10.1007/s11390-022-2158-x · Cited by 9
Improving Deliberation by Text-Only and Semi-Supervised Training
Hu, K., Sainath, T. N., He, Y., Prabhavalkar, R., Strohman, T., Mavandadi, S., & Wang, W. (2022) · Interspeech (USB) · doi:10.21437/interspeech.2022-243 · Cited by 11
Swahili Speech Dataset Development and Improved Pre-training Method for Spoken Digit Recognition
Kivaisi, A. R., Zhao, Q., & Mbelwa, J. (2023) · ACM Transactions on Asian and Low-Resource Language Information Processing · doi:10.1145/3597494 · Cited by 8
Park, S., Mark, M., Park, B., & Hong, H. (2023) · Computers, materials & continua/Computers, materials & continua (Print) · doi:10.32604/cmc.2023.041332 · Cited by 8
Generation-Based Target Speech Extraction with Speech Discretization and Vocoder
Yu, L., Zhang, W., Du, C., Zhang, L., Zheng, L., & Qian, Y. (2024) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp48485.2024.10446418 · Cited by 8
Active Learning with Task Adaptation Pre-training for Speech Emotion Recognition
Li, D., Zhang, Y., Wang, Y., Funakoshi, K., & Okumura, M. (2024) · Journal of Natural Language Processing · doi:10.5715/jnlp.31.825 · Cited by 10
Music Genre Classification- A Holistic Approach Employing Multiple Features
Anuraj, K., Poorna, S. S., & Renjith, S. (2024) · International Conference on Computing, Communication and Networking Technologies (ICCCNT) · doi:10.1109/icccnt61001.2024.10725629 · Cited by 8
Multilingual speech recognition initiative for African languages
Naira, A. M., Allak, A., Gaanoun, K., Benelallam, I., Erraji, Z., & Bahafid, A. (2024) · International Journal of Data Science and Analytics · doi:10.1007/s41060-024-00677-9 · Cited by 10
Learning VAE with Categorical Labels for Generating Conditional Handwritten Characters
Goto, K., & Inoue, N. (2021) · doi:10.23919/mva51890.2021.9511404 · Cited by 8
Weakly Supervised Construction of ASR Systems from Massive Video Data
Cheng, M., Wang, C., Huang, J., & Wang, X. (2021) · Interspeech (USB) · doi:10.21437/interspeech.2021-7 · Cited by 8
Yousefi, M., & Hansen, J. H. L. (2021) · IEEE Workshop on Automatic Speech Recognition and Understanding (ASRU) · doi:10.1109/asru51503.2021.9688231 · Cited by 8
Lee, S., Kim, H.-I., & Ro, Y. M. (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/cvpr52688.2022.01028 · Cited by 8
Cross-modal dynamic sentiment annotation for speech sentiment analysis
Chen, J., Sun, C., Zhang, S., & Zeng, J. (2023) · Computers & Electrical Engineering · doi:10.1016/j.compeleceng.2023.108598 · Cited by 8
A Generic Self-Supervised Framework of Learning Invariant Discriminative Features
Ntelemis, F., Jin, Y., & Thomas, S. A. (2023) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2023.3265607 · Cited by 8
Jang, K., Kim, S., Yun, S.-Y., & Kim, H. (2023) · Interspeech (USB) · doi:10.21437/interspeech.2023-1329 · Cited by 8
Coded Speech Quality Measurement by a Non-Intrusive PESQ-DNN
Xu, Z., Zhao, Z., & Fingscheidt, T. (2023) · IEEE/ACM Transactions on Audio Speech and Language Processing · doi:10.1109/taslp.2023.3317574 · Cited by 8
After: Active Learning Based Fine-Tuning Framework for Speech Emotion Recognition
Li, D., Wang, Y., Funakoshi, K., & Okumura, M. (2023) · IEEE Workshop on Automatic Speech Recognition and Understanding (ASRU) · doi:10.1109/asru57964.2023.10389652 · Cited by 8
Yu, J., Zhu, W., Zhu, J., Cai, Z., Zhao, G., Zhang, Z., Xie, G., Wei, Z., Liu, Q., & Liang, J. (2024) · IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw63382.2024.00490 · Cited by 8
Masumura, R., Makishima, N., Ihori, M., Takashima, A., Tanaka, T., & Orihashi, S. (2020) · Interspeech (USB) · doi:10.21437/interspeech.2020-1930 · Cited by 8
Le, H., Barbier, F., Nguyen, H., Tomashenko, N., Mdhaffar, S., Gahbiche, S., Lecouteux, B., Schwab, D., & Estève, Y. (2021) · International Conference on Spoken Language Translation (IWSLT) · doi:10.18653/v1/2021.iwslt-1.20 · Cited by 9
Towards Modelling Coherence in Spoken DiscoursePreprint
Patil, R., Singla, Y. K., Shah, R. R., Hama, M., & Zimmermann, R. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2101.00056 · Cited by 8
OkwuGbé: End-to-End Speech Recognition for Fon and IgboPreprint
Dossou, B. F. P., & Emezue, C. C. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2103.07762 · Cited by 8
Analysis of Predictive Coding Models for Phonemic Representation Learning in Small DatasetsPreprint
Blandón, M. A. C., & Räsänen, O. J. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2007.04205 · Cited by 8
Automatic Recognition of Continuous Malayalam Speech using Pretrained Multilingual Transformers
Manohar, K., Menon, G. G., Abraham, A., Rajan, R., & Jayan, A. R. (2023) · International Conference on Intelligent Systems for Communication, IoT and Security (ICISCoIS) · doi:10.1109/iciscois56541.2023.10100598 · Cited by 9
Speech Emotion Recognition Incorporating Relative Difficulty and Labeling Reliability
Ahn, Y., Han, S., Lee, S., & Shin, J. W. (2024) · Sensors · doi:10.3390/s24134111 · Cited by 7
Neural Orthodontic Staging: Predicting Teeth Movements With a Transformer
Ma, J., Lou, J., Jiang, B., Ye, H., Yu, W., Chen, X., Zhou, K., & Zheng, Y. (2024) · IEEE Transactions on Visualization and Computer Graphics · doi:10.1109/tvcg.2024.3504866 · Cited by 7
Robust Cross-Etiology and Speaker-Independent Dysarthric Speech Recognition
Singh, S., Wang, Q., Zhong, Z., Mendes, C., Hasegawa‐Johnson, M., Abdulla, W. H., & Shahamiri, S. R. (2025) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp49660.2025.10888041 · Cited by 7
CIEG-Net: Context Information Enhanced Gated Network for multimodal sentiment analysis
Chen, Z., Lu, C., & Wang, Y. (2025) · Pattern Recognition · doi:10.1016/j.patcog.2025.111785 · Cited by 8
Progress, challenges and future of linguistic neural decoding with deep learning
Wang, Y., Liu, H., Wang, Y., Xuan, C., Hou, Y., Feng, S., Liu, H., Liao, Y., & Wang, Y. (2025) · Communications Biology · doi:10.1038/s42003-025-08511-z · Cited by 10
A review on speech emotion recognition for low-resource and Indigenous languages
Rathnayake, H., James, J., Leoni, G., Nicholas, A., Watson, C. I., & Keegan, P. (2025) · Speech Communication · doi:10.1016/j.specom.2025.103342 · Cited by 7
He, J., Shi, X., Hu, C.-H., Mi, J., Li, X., & Toda, T. (2025) · IEEE Transactions on Audio Speech and Language Processing · doi:10.1109/taslpro.2025.3614428 · Cited by 7
Improving Label-Deficient Keyword Spotting Through Self-Supervised Pretraining
Bovbjerg, H. S., & Tan, Z. (2023) · IEEE International Conference on Acoustics, Speech, and Signal Processing Workshops (ICASSPW) · doi:10.1109/icasspw59220.2023.10193371 · Cited by 7
Augmentation Techniques for Adult-Speech to Generate Child-Like Speech Data Samples at Scale
Yiwere, M. Y., Barcovschi, A., Jain, R., Cucu, H., & Corcoran, P. (2023) · IEEE Access · doi:10.1109/access.2023.3317360 · Cited by 7
Slaughter, I., Greenberg, C. S., Schwartz, R., & Caliskan, A. (2023) · Findings of the Association for Computational Linguistics: EMNLP (Findings of EMNLP) · doi:10.18653/v1/2023.findings-emnlp.602 · Cited by 12
Deep temporal clustering features for speech emotion recognition
Lin, W.-C., & Busso, C. (2024) · Speech Communication · doi:10.1016/j.specom.2023.103027 · Cited by 7
Transfer Learning for Low-Resource, Multi-Lingual, and Zero-Shot Multi-Speaker Text-to-Speech
Jeong, M., Kim, M., Choi, B. J., Yoon, J., Jang, W., & Kim, N. S. (2024) · IEEE/ACM Transactions on Audio Speech and Language Processing · doi:10.1109/taslp.2024.3364085 · Cited by 7
AudioRepInceptionNeXt: A lightweight single-stream architecture for efficient audio recognition
Lau, K. W., Rehman, Y. A. U., & Po, L.-M. (2024) · Neurocomputing · doi:10.1016/j.neucom.2024.127432 · Cited by 7
Cubic Knowledge Distillation for Speech Emotion Recognition
Lou, Z., Otake, S., Li, Z., Kawakami, R., & Inoue, N. (2024) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp48485.2024.10447713 · Cited by 7
DenoSent: A Denoising Objective for Self-Supervised Sentence Representation Learning
Wang, X., He, J., Wang, P., Zhou, Y., Sun, T., & Qiu, X. (2024) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v38i17.29886 · Cited by 8
Deep Active Audio Feature Learning in Resource-Constrained Environments
Mohaimenuzzaman, M., Bergmeir, C., & Meyer, B. E. (2024) · IEEE/ACM Transactions on Audio Speech and Language Processing · doi:10.1109/taslp.2024.3416697 · Cited by 9
Rizhinashvili, D., Sham, A. H., & Anbarjafari, G. (2024) · Signal Image and Video Processing · doi:10.1007/s11760-024-03406-8 · Cited by 7
Choi, J., Park, S. J., Kim, M., & Ro, Y. M. (2024) · 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/cvpr52733.2024.02580 · Cited by 9
Zhang, Z., Xu, W., Dong, Z., Wang, K., Wu, Y., Peng, J., Wang, R., & Huang, D. (2024) · IEEE Transactions on Affective Computing · doi:10.1109/taffc.2024.3506554 · Cited by 8
Integrating Fine-Tuned LLM With Acoustic Features for Enhanced Detection of Alzheimer's Disease
Casu, F., Lagorio, A., Ruiu, P., Trunfio, G. A., & Grosso, E. (2025) · IEEE Journal of Biomedical and Health Informatics · doi:10.1109/jbhi.2025.3566615 · Cited by 7
Zhu, Q., Zhang, J., Wu, M., Fang, X., & Dai, L.-R. (2021) · Interspeech (USB) · doi:10.21437/interspeech.2021-67 · Cited by 7
Auto-KWS 2021 Challenge: Task, Datasets, and Baselines
Wang, J., He, Y., Zhao, C., Shao, Q., Tu, W.-W., Ko, T., Lee, H.-Y., & Xie, L. (2021) · Interspeech (USB) · doi:10.21437/interspeech.2021-817 · Cited by 7
Joint Encoder-Decoder Self-Supervised Pre-training for ASR
Arunkumar, A., & Umesh, S. (2022) · Interspeech (USB) · doi:10.21437/interspeech.2022-11338 · Cited by 7
On-demand compute reduction with stochastic wav2vec 2.0
Vyas, A., Hsu, W.-N., Auli, M., & Baevski, A. (2022) · Interspeech (USB) · doi:10.21437/interspeech.2022-10584 · Cited by 7
Self-citationZero-shot Voice Conversion via Self-supervised Prosody Representation Learning
Wang, S., & Borth, D. (2022) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn55064.2022.9892405 · Cited by 8
Predictive AutoEncoders Are Context-Aware Unsupervised Anomalous Sound Detectors
Zeng, X., Song, Y., Dai, L.-R., & Liu, L. (2023) · Communications in computer and information science · doi:10.1007/978-981-99-2401-1_9 · Cited by 7
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
