The DOI matches its Crossref record; 33 of the 33 references it cites were found in a registry or an index.
Conformer: Convolution-augmented Transformer for Speech Recognition
Open accessAbstract
Recently Transformer and Convolution neural network (CNN) based models have shown promising results in Automatic Speech Recognition (ASR), outperforming Recurrent neural networks (RNNs). Transformer models are good at capturing content-based global interactions, while CNNs exploit local features effectively. In this work, we achieve the best of both worlds by studying how to combine convolution neural networks and transformers to model both local and global dependencies of an audio sequence in a parameter-efficient way. To this regard, we propose the convolution-augmented transformer for speech recognition, named Conformer. Conformer significantly outperforms the previous Transformer and CNN based models achieving state-of-the-art accuracies. On the widely used LibriSpeech benchmark, our model achieves WER of 2.1%/4.3% without using a language model and 1.9%/3.9% with an external language model on test/testother. We also observe competitive performance of 2.7%/6.3% with a small model of only 10M parameters.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
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?
In the citing paper
“In particular, transformer1 and recurrent neural-network transducer (RNNT)12,13,16 models containing up to one billion parameters2 have produced a marked decrease in word error rate (WER) (and therefore much better accuracy) for the automated transcription of spoken English-language sentences, as shown in Fig. 1a for two widely used datasets, Librispeech17 and SwitchBoard18.”
From An analog-AI chip for energy-efficient speech recognition and transcription (2023) · cites this paper as [16]
In the citing paper
“A range of acoustic models that give state-of-the-art performance on these tasks are chosen as the baseline speech recognition systems, including hybrid DNN [41], hybrid lattice-free maximum mutual information (LF-MMI) trained time delay neural network (TDNN) [3] and end-to-end (E2E) Conformer [6] models.”
From Speaker adaptation using spectro-temporal deep features for dysarthric and elderly speech recognition (2022) · cites this paper as [6]
Citations
Cites
Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A. N., Kaiser, L., & Polosukhin, I. (2017) · arXiv · doi:10.48550/arxiv.1706.03762 · Cited by 120,404
Self-citationAdam: A Method for Stochastic Optimization
Kingma, D. P., & Ba, J. (2014) · arXiv · doi:10.48550/arxiv.1412.6980 · Cited by 98,946
Squeeze-and-Excitation NetworksPreprint
Hu, J., Shen, L., & Sun, G. (2017) · 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition · doi:10.48550/arxiv.1709.01507 · Cited by 37,845
(2014) · Cited by 33,419
Squeeze-and-Excitation Networks
Hu, J., Shen, L., Albanie, S., Sun, G., & Wu, E. (2020) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2019.2913372 · Cited by 12,157
“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
SpecAugment: A Simple Data Augmentation Method for Automatic Speech Recognition
Park, D. S., Chan, W., Zhang, Y., Chiu, C.-C., Zoph, B., Cubuk, E. D., & Le, Q. V. (2019) · Interspeech 2019 · doi:10.21437/interspeech.2019-2680 · Cited by 3,558
Self-citationTransformer-XL: Attentive language models beyond a fixed-length context
Dai, Z., Yang, Z., Yang, Y., Carbonell, J., Le, Q., & Salakhutdinov, R. (2019) · Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics · doi:10.18653/v1/p19-1285 · Cited by 3,169
Searching for activation functions
Ramachandran, P., Zoph, B., & Le, Q. V. (2017) · arXiv · doi:10.48550/arxiv.1710.05941 · Cited by 2,335
Convolutional Neural Networks for Speech Recognition
Abdel‐Hamid, O., Mohamed, A., Jiang, H., Deng, L., Penn, G., & Yu, D. (2014) · IEEE/ACM Transactions on Audio Speech and Language Processing · doi:10.1109/taslp.2014.2339736 · Cited by 2,325
Cited by
Sorted by citations
Items 1,001–1,004 of 1,004
Proposal-based Few-shot Sound Event Detection for Speech and Environmental Sounds with PerceiversPreprint
Wolters, P., Sizemore, L., Daw, C., Hutchinson, B., & Phillips, L. A. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2107.13616 · Cited by 15
SpeechNet: A Universal Modularized Model for Speech Processing Tasks
Chen, Y.-C., Chi, P.-H., Yang, S.-W., Chang, K.-W., Lin, J.-H., Huang, S.-F., Liu, D.-R., Liu, C.-L., Lee, C.-K., & Lee, H.-Y. (2021) · arXiv · doi:10.48550/arxiv.2105.03070 · Cited by 6
Attentional multi-feature fusion for spoofing-aware speaker verification
Shen, Q., Guo, M., Huang, Y., & Ma, J. (2024) · International Journal of Speech Technology · doi:10.1007/s10772-024-10112-w · Cited by 5
wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representations
Baevski, A., Zhou, H., Mohamed, A., & Auli, M. (2020) · arXiv · doi:10.48550/arxiv.2006.11477 · Cited by 2,369
Metadata
- Authors
- Gulati, A., Qin, J., Chiu, C.-C., Parmar, N., Zhang, Y., Yu, J., Han, W., Wang, S., Zhang, Z., Wu, Y., & Pang, R.
- Affiliations
- Google (United States) (US)
- ORCID
- Venue
- Interspeech 2020
- Publisher
- ISCA
- Published
- 2020-10-25
- Pages
- 5036-5040
- ISSN
- 2308-457X (ISSN-L)
- OpenAlex
- W3097777922
- Cited by
- 3,150
- References
- 33
- Citations by year
- 2026: 373 · 2025: 666 · 2024: 644 · 2023: 708 · 2022: 424 · 2021: 300 · 2020: 35
- FWCI
- 140.10
- 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)
- 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
- conformational isomers, speech recognition, CNN-Transformer hybrid, parameter-efficient models, LibriSpeech, word error rate
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.
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
