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
13 Own result · 7 Not checked yet · 3 Own interpretation · 2 No basis given · 1 Own method
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
plainn = 10- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
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 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
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
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 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
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
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
“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
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- 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
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
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 4 shows that a crop size of 150k frames results in the best performance.”
§ WAV2VEC: UNSUPERVISED PRE-TRAINING FOR SPEECH RECOGNITION > 4.3 ABLATIONS
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
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 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
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
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
“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
boosteddirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- 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
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
In 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
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- 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
boosteddirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It 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
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably 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
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It 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
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It 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
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It 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
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It 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
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It 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
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
It 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
plaindirect- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: fails — The paper’s conclusions may not depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably 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
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
Probably 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
Cited by
Sorted by citations
Items 401–500 of 1,003
Frame-Level Emotional State Alignment Method for Speech Emotion Recognition
Li, Q., Gao, Y., Wang, C., Deng, Y., Xue, J., Han, Y., & Li, Y. (2024) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp48485.2024.10446812 · Cited by 17
Whisper-SV: Adapting Whisper for low-data-resource speaker verification
Zhang, L., Jiang, N., Wang, Q., Li, Y., Lu, Q., & Xie, L. (2024) · Speech Communication · doi:10.1016/j.specom.2024.103103 · Cited by 15
ELP-Adapters: Parameter Efficient Adapter Tuning for Various Speech Processing Tasks
Inoue, N., Otake, S., Hirose, T., Ohi, M., & Kawakami, R. (2024) · IEEE/ACM Transactions on Audio Speech and Language Processing · doi:10.1109/taslp.2024.3434445 · Cited by 16
Jiao, X., Wang, L., & Yu, Y. (2024) · IEEE International Conference on Multimedia and Expo (ICME) · doi:10.1109/icme57554.2024.10688053 · Cited by 15
Joint Speech-Text Embeddings for Multitask Speech Processing
Gonzales, M. G., Corcoran, P., Harte, N., & Schukat, M. (2024) · IEEE Access · doi:10.1109/access.2024.3473743 · Cited by 17
High-Fidelity Audio Generation and Representation Learning With Guided Adversarial Autoencoder
Haque, K. N., Rana, R. K., & Schuller, B. W. (2020) · IEEE Access · doi:10.1109/access.2020.3040797 · Cited by 18
Comparing CTC and LFMMI for Out-of-Domain Adaptation of wav2vec 2.0 Acoustic Model
Vyas, A., Madikeri, S. R., & Bourlard, H. A. (2021) · Interspeech (USB) · doi:10.21437/interspeech.2021-1683 · Cited by 15
Venugopalan, S., Shor, J., Plakal, M., Tobin, J., Tomanek, K., Green, J. R., & Brenner, M. P. (2021) · Interspeech (USB) · doi:10.21437/interspeech.2021-1913 · Cited by 18
A Study of Gender Impact in Self-supervised Models for Speech-to-Text Systems
Boito, M. Z., Besacier, L., Tomashenko, N., & Estève, Y. (2022) · Interspeech (USB) · doi:10.21437/interspeech.2022-353 · Cited by 23
Speech Driven Tongue Animation
Medina, S., Tomè, D., Stoll, C., Tiede, M., Munhall, K. G., Hauptmann, A. G., & Matthews, I. (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/cvpr52688.2022.01976 · Cited by 19
A Context-Aware Knowledge Transferring Strategy for CTC-Based ASR
Lu, K.-H., & Chen, K.-Y. (2023) · IEEE Spoken Language Technology Workshop (SLT) · doi:10.1109/slt54892.2023.10022825 · Cited by 15
Kessler, S., Thomas, B., & Karout, S. A. (2021) · arXiv (Cornell University) · Cited by 15
Ada2I: Enhancing Modality Balance for Multimodal Conversational Emotion Recognition
Nguyen, C.-V. T., Le, T.-S., Mai, A.-T., & Le, D.-T. (2024) · ACM International Conference on Multimedia (ACM MM) · doi:10.1145/3664647.3681648 · Cited by 14
Multi-Level Contrastive Learning for Multimodal Sentiment Analysis
Yan, Z., Bai, W., Zhang, Y., Deng, J., Hu, Z., Zhang, X., & Ren, F. (2025) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2025.3613116 · Cited by 16
Self-Supervised End-to-End ASR for Low Resource L2 Swedish
Al-Ghezi, R., Getman, Y., Rouhe, A., Hildén, R., & Kurimo, M. (2021) · Interspeech (USB) · doi:10.21437/interspeech.2021-1710 · Cited by 19
Improved Transformer With Multi-Head Dense Collaboration
Wang, H., Shen, X., Tu, M., Zhuang, Y., & Liu, Z. (2022) · IEEE/ACM Transactions on Audio Speech and Language Processing · doi:10.1109/taslp.2022.3199648 · Cited by 15
Disentangling Prosody Representations With Unsupervised Speech Reconstruction
Qu, L., Li, T., Weber, C., Rosin, T. P., Ren, F., & Wermter, S. (2023) · IEEE/ACM Transactions on Audio Speech and Language Processing · doi:10.1109/taslp.2023.3320864 · Cited by 17
Multi-objective non-intrusive hearing-aid speech assessment model
Chiang, H.-T., Fu, S., Wang, H., Tsao, Y., & Hansen, J. H. L. (2024) · The Journal of the Acoustical Society of America · doi:10.1121/10.0034362 · Cited by 14
Developing a negative speech emotion recognition model for safety systems using deep learning
Jena, S., Basak, S., Agrawal, H., Saini, B., Gite, S., Kotecha, K. V., & Alfarhood, S. (2025) · Journal Of Big Data · doi:10.1186/s40537-025-01090-0 · Cited by 14
Contrastive Predictive Coding of Audio with an Adversary
Wang, L., Kawakami, K., & van den Oord, A. (2020) · Interspeech (USB) · doi:10.21437/interspeech.2020-1891 · Cited by 14
DAP: Detection-Aware Pre-training with Weak Supervision
Zhong, Y., Wang, J., Wang, L., Peng, J., Wang, Y.-X., & Zhang, L. (2021) · 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/cvpr46437.2021.00451 · Cited by 14
Wang, C., Li, Z., Tang, B., Yin, X., Wan, Y., Yu, Y., & Ma, Z. (2022) · Interspeech (USB) · doi:10.21437/interspeech.2022-10316 · Cited by 14
Cascade or Direct Speech Translation? A Case Study
Etchegoyhen, T., Arzelus, H., Gete, H., Álvarez, A., Torre, I. G., Martín-Doñas, J. M., González-Docasal, A., & Fernandez, E. B. (2022) · Applied Sciences · doi:10.3390/app12031097 · Cited by 14
TENET: A Time-Reversal Enhancement Network for Noise-Robust ASR
Chao, F.-A., Jiang, S., Yan, B.-C., Hung, J.-W., & Chen, B. (2021) · IEEE Workshop on Automatic Speech Recognition and Understanding (ASRU) · doi:10.1109/asru51503.2021.9687924 · Cited by 16
Thienpondt, J., & Demuynck, K. (2022) · Interspeech (USB) · doi:10.21437/interspeech.2022-10964 · Cited by 17
Decomposition and Reorganization of Phonetic Information for Speaker Embedding Learning
Hong, Q.-B., Wu, C., & Wang, H. (2023) · IEEE/ACM Transactions on Audio Speech and Language Processing · doi:10.1109/taslp.2023.3267833 · Cited by 14
Improving Streaming Transformer Based ASR Under a Framework of Self-Supervised Learning
Cao, S., Kang, Y., Fu, Y., Xu, X., Sun, S., Zhang, Y., & Ma, L. (2021) · Interspeech (USB) · doi:10.21437/interspeech.2021-1454 · Cited by 17
Multimodal Referring Segmentation: A Survey
Ding, H., Tang, S., He, S., Liu, C., Wu, Z., & Jiang, Y. (2026) · International Journal of Computer Vision · doi:10.1007/s11263-026-02943-8 · Cited by 36
Contrastive Siamese Network for Semi-Supervised Speech Recognition
Khorram, S., Kim, J., Tripathi, A., Han, L., Zhang, Q., & Sak, H. (2022) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp43922.2022.9747355 · Cited by 13
Self-Supervised Training of Speaker Encoder With Multi-Modal Diverse Positive Pairs
Tao, R., Lee, K. A., Das, R. K., Hautamäki, V., & Li, H. (2023) · IEEE/ACM Transactions on Audio Speech and Language Processing · doi:10.1109/taslp.2023.3268568 · Cited by 15
MGAT: Multi-Granularity Attention Based Transformers for Multi-Modal Emotion Recognition
Fan, W., Xing, X., Cai, B., & Xu, X. (2023) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp49357.2023.10095855 · Cited by 13
Speaker Adaptive Text-to-Speech With Timbre-Normalized Vector-Quantized Feature
Du, C., Guo, Y., Chen, X., & Yu, K. (2023) · IEEE/ACM Transactions on Audio Speech and Language Processing · doi:10.1109/taslp.2023.3308374 · Cited by 13
Kazakh Speech Recognition: Wav2vec2.0 vs. Whisper
Kozhirbayev, Z. (2023) · Journal of Advances in Information Technology · doi:10.12720/jait.14.6.1382-1389 · Cited by 17
Nasersharif, B., & Namvarpour, M. (2024) · The Journal of Supercomputing · doi:10.1007/s11227-024-06158-x · Cited by 13
ON-TRAC Consortium Systems for the IWSLT 2022 Dialect and Low-resource Speech Translation Tasks
Boito, M. Z., Ortega, J., Riguidel, H., Laurent, A., Barrault, L., Bougares, F., Chaabani, F., Nguyen, H., Barbier, F., Gahbiche, S., et al. (2022) · International Conference on Spoken Language Translation (IWSLT) · doi:10.18653/v1/2022.iwslt-1.28 · Cited by 15
Learning Contextually Fused Audio-Visual Representations For Audio-Visual Speech Recognition
Zhang, Z., Zhang, J., Zhang, J.-S., Wu, M., Fang, X., & Dai, L.-R. (2022) · Proceedings - International Conference on Image Processing · doi:10.1109/icip46576.2022.9897235 · Cited by 14
Sullivan, P., Shibano, T., & Abdul-Mageed, M. (2022) · Signals and communication technology · doi:10.1007/978-3-031-11035-1_2 · Cited by 13
Stoewer, P., Schilling, A., Maier, A., & Krauß, P. (2023) · Scientific Reports · doi:10.1038/s41598-023-30307-6 · Cited by 16
Unsupervised Learning of Disentangled Speech Content and Style Representation
Tjandra, A., Pang, R., Zhang, Y., & Karita, S. (2021) · Interspeech (USB) · doi:10.21437/interspeech.2021-1936 · Cited by 19
Hierarchical Phone Recognition with Compositional Phonetics
Li, X., Li, J., Metze, F., & Black, A. W. (2021) · Interspeech (USB) · doi:10.21437/interspeech.2021-1803 · Cited by 14
Self-Supervised Learning With Segmental Masking for Speech Representation
Yue, X., Lin, J., Ritter-Gutierrez, F., & Li, H. (2022) · IEEE Journal of Selected Topics in Signal Processing · doi:10.1109/jstsp.2022.3191845 · Cited by 13
Assessment Modeling: Fundamental Pre-training Tasks for Interactive Educational SystemsPreprint
Choi, Y., Lee, Y., Cho, J., Baek, J., Shin, D., Yu, H., Shim, Y., Lee, S., Shin, J., Bae, C., et al. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2002.05505 · Cited by 14
Learning Speech Representations from Raw Audio by Joint Audiovisual Self-SupervisionPreprint
Shukla, A., Petridis, S., & Pantić, M. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2007.04134 · Cited by 15
Improving Perceptual Quality by Phone-Fortified Perceptual Loss for Speech Enhancement.Preprint
Hsieh, T.-A., Yu, C., Fu, S., Lu, X., & Tsao, Y. (2020) · arXiv (Cornell University) · Cited by 13
Supervision-Guided Codebooks for Masked Prediction in Speech Pre-training
Wang, C., Wang, Y., Wu, Y., Chen, S., Li, J., Liu, S., & Wei, F. (2022) · Interspeech (USB) · doi:10.21437/interspeech.2022-936 · Cited by 12
Improving Hypernasality Estimation with Automatic Speech Recognition in Cleft Palate Speech
Song, K., Wan, T., Wang, B., Jiang, H., Qiu, L., Xu, J., Jiang, L., Lou, Q., Yang, Y., Li, D., et al. (2022) · Interspeech (USB) · doi:10.21437/interspeech.2022-438 · Cited by 13
Speech Separation With Pretrained Frontend to Minimize Domain Mismatch
Wang, W., Pan, Z., Li, X., Wang, S., & Li, H. (2024) · IEEE/ACM Transactions on Audio Speech and Language Processing · doi:10.1109/taslp.2024.3446242 · Cited by 13
Deng, Y., Bian, J., Wu, S., Lai, J., & Xie, X. (2024) · Information Fusion · doi:10.1016/j.inffus.2024.102711 · Cited by 12
Angra, A., Muralikrishna, H., Dinesh, D. A., & Thenkanidiyoor, V. (2024) · IEEE Access · doi:10.1109/access.2024.3523951 · Cited by 14
Fan, W., Xu, X., Guohua, Z., Deng, X., & Xing, X. (2025) · Speech Communication · doi:10.1016/j.specom.2025.103198 · Cited by 12
Kawamura, H., Miura, T., Maeda, Y., Okada, Y., & Zempo, K. (2025) · IEEE Access · doi:10.1109/access.2025.3573648 · Cited by 12
Ditthapron, A., Lammert, A. C., & Agu, E. (2022) · IEEE Journal of Biomedical and Health Informatics · doi:10.1109/jbhi.2022.3158840 · Cited by 15
Filler Word Detection and Classification: A Dataset and Benchmark
Zhu, G., Cáceres, J.-P., & Salamon, J. (2022) · Interspeech (USB) · doi:10.21437/interspeech.2022-10992 · Cited by 12
On the Use of External Data for Spoken Named Entity Recognition
Pasad, A., Wu, F., Shon, S., Livescu, K., & Han, K. (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.53 · Cited by 12
Research on Chinese Speech Emotion Recognition Based on Deep Neural Network and Acoustic Features
Lee, M.-C., Yeh, S., Chang, J.-W., & Chen, Z.-Y. (2022) · Sensors · doi:10.3390/s22134744 · Cited by 12
Recent improvements of ASR models in the face of adversarial attacks
Olivier, R., & Raj, B. (2022) · Interspeech (USB) · doi:10.21437/interspeech.2022-400 · Cited by 12
Sound Localization by Self-supervised Time Delay Estimation
Chen, Z., Fouhey, D. F., & Owens, A. (2022) · Lecture notes in computer science · doi:10.1007/978-3-031-19809-0_28 · Cited by 12
Self-Supervised Audio-Visual Speech Representations Learning by Multimodal Self-Distillation
Zhang, J., Wan, G., Ling, Z.-H., Pan, J., Gao, J., & Liu, C. (2023) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp49357.2023.10095029 · Cited by 12
Fast Yet Effective Speech Emotion Recognition with Self-Distillation
Ren, Z. X., Nguyên, T. T., Chang, Y. H., & Schuller, B. W. (2023) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp49357.2023.10094895 · Cited by 12
Self-supervised learning for robust object retrieval without human annotations
den Herrewegen, J. V., Tourwé, T., & wyffels, F. (2023) · Computers & Graphics · doi:10.1016/j.cag.2023.06.029 · Cited by 12
Predicting Word Error Rate for Reverberant Speech
Gamper, H., Emmanouilidou, D., Braun, S., & Tashev, I. (2020) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp40776.2020.9053025 · Cited by 12
Haque, K. N., Rana, R. K., Liu, J., Hansen, J. H. L., Cummins, N., Busso, C., & Schuller, B. W. (2021) · IEEE/ACM Transactions on Audio Speech and Language Processing · doi:10.1109/taslp.2021.3098764 · Cited by 13
Multi-modal Fusion for Video Sentiment Analysis
Li, R., Zhao, J., Hu, J., Guo, S., & Jin, Q. (2020) · doi:10.1145/3423327.3423671 · Cited by 13
HarperValleyBank: A Domain-Specific Spoken Dialog CorpusPreprint
Wu, M., Nafziger, J., Scodary, A., & Maas, A. L. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2010.13929 · Cited by 12
Hsieh, T.-A., Yu, C., Fu, S., Lu, X., & Tsao, Y. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2010.15174 · Cited by 12
Textless Speech Emotion Conversion using Decomposed and Discrete RepresentationsPreprint
Kreuk, F., Polyak, A., Copet, J., Kharitonov, E., Nguyen, T. A., Rivière, M., Hsu, W.-N., Mohamed, A., Emmanuel Dupoux, A., & Adi, Y. (2021) · arXiv (Cornell University) · Cited by 12
A Performance Benchmarking Review of Transformers for Speaker-Independent Speech Emotion Recognition
Portal, F., de Lope, J., & Graña, M. (2025) · International Journal of Neural Systems · doi:10.1142/s0129065725300013 · Cited by 11
K-Wav2vec 2.0: Automatic Speech Recognition based on Joint Decoding of Graphemes and Syllables
Kim, J., & Kang, P. (2022) · Interspeech (USB) · doi:10.21437/interspeech.2022-547 · Cited by 15
Vitale, V. N., Cutugno, F., Origlia, A., & Coro, G. (2024) · Neural Computing and Applications · doi:10.1007/s00521-024-09435-1 · Cited by 16
Voice-Augmented Virtual Reality Interface for Serious Games
Aslam, F., & Zhao, R. (2024) · IEEE Conference on Games (CoG) · doi:10.1109/cog60054.2024.10645616 · Cited by 11
Multilingual Meta-Transfer Learning for Low-Resource Speech Recognition
Zhou, R., Koshikawa, T., Ito, A., Nose, T., & Chen, C.-P. (2024) · IEEE Access · doi:10.1109/access.2024.3486711 · Cited by 11
SeeNet: A Soft Emotion Expert and Data Augmentation Method to Enhance Speech Emotion Recognition
Li, Q., Gao, Y., Wen, Y., Zhao, Z., Li, Y., & Schuller, B. W. (2025) · IEEE Transactions on Affective Computing · doi:10.1109/taffc.2025.3555406 · Cited by 11
Klempíř, O., Skryjova, A., Tichopád, A., & Krupička, R. (2025) · Computational and Structural Biotechnology Journal · doi:10.1016/j.csbj.2025.06.022 · Cited by 13
Enabling Interactive Transcription in an Indigenous Community
Ferrand, É. L., Bird, S., & Besacier, L. (2020) · International Conference on Computational Linguistics · doi:10.18653/v1/2020.coling-main.303 · Cited by 11
Enhancing Audio Augmentation Methods with Consistency Learning
Iqbal, T., Helwani, K., Krishnaswamy, A., & Wang, W. (2021) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp39728.2021.9414316 · Cited by 11
Zero-Shot Cross-Lingual Phonetic Recognition with External Language Embedding
Gao, H., Ni, J., Zhang, Y., Qian, K., Chang, S., & Hasegawa‐Johnson, M. (2021) · Interspeech (USB) · doi:10.21437/interspeech.2021-1843 · Cited by 11
ScSer: Supervised Contrastive Learning for Speech Emotion Recognition using Transformers
Alaparthi, V. S., Pasam, T. R., Inagandla, D. A., Prakash, J., & Singh, P. K. (2022) · Conference on Human System Interactions · doi:10.1109/hsi55341.2022.9869453 · Cited by 11
PHQ-V/GAD-V: Assessments to Identify Signals of Depression and Anxiety from Patient Video Responses
Grimm, B., Talbot, B., & Larsen, L. (2022) · Applied Sciences · doi:10.3390/app12189150 · Cited by 11
Unsupervised Data Selection via Discrete Speech Representation for ASR
Lu, Z., Wang, Y., Zhang, Y., Han, W., Chen, Z., & Haghani, P. (2022) · Interspeech (USB) · doi:10.21437/interspeech.2022-399 · Cited by 11
End-to-End Model-Based Detection of Infants with Autism Spectrum Disorder Using a Pretrained Model
Lee, J. H., Lee, G. W., Bong, G., Yoo, H. J., & Kim, H. K. (2022) · Sensors · doi:10.3390/s23010202 · Cited by 11
Lin, Z., Zeng, B., Hu, H., Huang, Y., Xu, L., & Yao, Z. (2023) · Knowledge-Based Systems · doi:10.1016/j.knosys.2023.110396 · Cited by 13
End-to-End Mispronunciation Detection and Diagnosis Using Transfer Learning
Peng, L., Gao, Y., Bao, R., Li, Y., & Zhang, J. (2023) · Applied Sciences · doi:10.3390/app13116793 · Cited by 12
Lin, Y., Wang, L., Yang, Y., & Dang, J. (2023) · IEEE/ACM Transactions on Audio Speech and Language Processing · doi:10.1109/taslp.2023.3319276 · Cited by 11
A multi-purpose audio-visual corpus for multi-modal Persian speech recognition: The Arman-AV dataset
Peymanfard, J., Heydarian, S., Lashini, A., Zeinali, H., Mohammadi, M. R., & Mozayani, N. (2023) · Expert Systems with Applications · doi:10.1016/j.eswa.2023.121648 · Cited by 11
The Applicability of Wav2Vec2 and Whisper for Low-Resource Maltese ASR
Williams, A., DeMarco, A., & Borg, C. (2023) · doi:10.21437/sigul.2023-9 · Cited by 11
Feng, T., Hebbar, R., & Narayanan, S. S. (2024) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp48485.2024.10446616 · Cited by 11
Nistal, J., Aouameur, C., Lattner, S., & Gaël Richard, A. (2021) · IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA) · doi:10.1109/waspaa52581.2021.9632757 · Cited by 11
Word-Level Embeddings for Cross-Task Transfer Learning in Speech Processing
Beckmann, P., Kegler, M., & Cerňak, M. (2021) · European Signal Processing Conference (EUSIPCO) · doi:10.23919/eusipco54536.2021.9616254 · Cited by 11
A Practical Guide to Logical Access Voice Presentation Attack Detection
Wang, X., & Yamagishi, J. (2022) · Studies in autonomic, data-driven and industrial computing · doi:10.1007/978-981-19-1524-6_8 · Cited by 11
Multilevel Transformer for Multimodal Emotion Recognition
He, J., Wu, M., Li, M., Zhu, X., & Ye, F. (2023) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp49357.2023.10097110 · Cited by 11
Mandarin-English Code-switching Speech Recognition with Self-supervised Speech Representation ModelsPreprint
Tseng, L.-H., Fu, Y.-K., Chang, H.-J., & Lee, H.-Y. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2110.03504 · Cited by 18
Manikandan, V., & Neethirajan, S. R. (2024) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.1101/2024.12.18.629057 · Cited by 11
Cross-Lingual Bimodal Emotion Recognition with LLM-Based Label Smoothing
Рюмина, Е. В., Axyonov, A., Abdulkadirov, T., Koryakovskaya, D., & Ryumin, D. (2025) · Big Data and Cognitive Computing · doi:10.3390/bdcc9110285 · Cited by 10
Self-supervised learning based domain regularization for mask-wearing speaker verification
Zhang, R., Wei, J., Lu, X., Lu, W., Jin, D., Zhang, L., Ji, Y., & Xu, J. (2023) · Speech Communication · doi:10.1016/j.specom.2023.102953 · Cited by 10
Islam, B., McElwain, N. L., Li, J., Davila, M. I., Hu, Y., Hu, K., Bodway, J. M., Dhekne, A., Choudhury, R. R., & Hasegawa‐Johnson, M. (2024) · Sensors · doi:10.3390/s24030901 · Cited by 11
Chen, H., Wang, Q., Du, J., Yin, B., Pan, J., & Lee, C. (2024) · IEEE/ACM Transactions on Audio Speech and Language Processing · doi:10.1109/taslp.2024.3393732 · Cited by 10
BaseNet: A transformer-based toolkit for nanopore sequencing signal decoding
Li, Q.-W., Sun, C., Wang, D., & Lou, J. (2024) · bioRxiv · doi:10.1016/j.csbj.2024.09.016 · Cited by 9
Expression Prompt Collaboration Transformer for universal referring video object segmentation
Chen, J., Lin, J., Zhong, G., Fu, H., Nai, K., Yang, K., & Li, Z. (2025) · Knowledge-Based Systems · doi:10.1016/j.knosys.2025.113006 · Cited by 12
Advancing ASR for Indian-Accented English: Dataset Creation and Whisper Fine-Tuning
Jaswanth, K., Ramachandrula, P., Sruthi, S., Vekkot, S., & Gupta, D. (2025) · Procedia Computer Science · doi:10.1016/j.procs.2025.04.513 · Cited by 10
Melshin, G., DiMaggio, A., Zeramdini, N., Mackinley, M., Palaniyappan, L. K., & Voppel, A. (2025) · NPP—Digital Psychiatry and Neuroscience · doi:10.1038/s44277-025-00040-1 · Cited by 11
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
