Recurrent Neural Network Transducer for Audio-Visual Speech Recognition
Open accessThe DOI matches its Crossref record; 9 of the 9 references it cites were found in a registry or an index.
Abstract
This work presents a large-scale audio-visual speech recognition system based on a recurrent neural network transducer (RNN-T) architecture. To support the development of such a system, we built a large audio-visual (A/V) dataset of segmented utterances extracted from YouTube public videos, leading to 31k hours of audio-visual training content. The performance of an audio-only, visual-only, and audio-visual system are compared on two large-vocabulary test sets: a set of utterance segments from public YouTube videos called YTDEV18 and the publicly available LRS3-TED set. To highlight the contribution of the visual modality, we also evaluated the performance of our system on the YTDEV18 set artificially corrupted with background noise and overlapping speech. To the best of our knowledge, our system significantly improves the state-of-the-art on the LRS3-TED set.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
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
FaceNet: A unified embedding for face recognition and clustering
Schroff, F., Kalenichenko, D., & Philbin, J. (2015) · 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2015.7298682 · Cited by 15,267
Davis, S., & Mermelstein, P. (1980) · IEEE Transactions on Acoustics, Speech, and Signal Processing · doi:10.1109/tassp.1980.1163420 · Cited by 5,465
Graves, A., Fernández, S., Gomez, F., & Schmidhuber, J. (2006) · Proceedings of the 23rd international conference on Machine learning - ICML '06 · doi:10.1145/1143844.1143891 · Cited by 5,370
Wu, Y., & He, K. (2020) · International Journal of Computer Vision · doi:10.1007/s11263-019-01198-w · Cited by 3,601
Visual Contribution to Speech Intelligibility in Noise
Sumby, W. H., & Pollack, I. (1954) · The Journal of the Acoustical Society of America · doi:10.1121/1.1907309 · Cited by 2,583
Deep Audio-Visual Speech Recognition
Afouras, T., Chung, J. S., Senior, A., Vinyals, O., & Zisserman, A. (2022) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2018.2889052 · Cited by 801
Lip reading sentences in the wild
Chung, J. S., Senior, A., Vinyals, O., & Zisserman, A. (2017) · 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2017.367 · Cited by 702 · cited 1×
“eir corresponding closed-captions provided by the BBC, they applied computer vision techniques to select short audio segments with an on-screen speaking face matching the audio. In subsequent studies [21, 22], they extended their approach to a larger amount of data, leading to the LRS2 & LRS3 datasets consisting o…”
Chung, J. S., & Zisserman, A. (2017) · Lecture Notes in Computer Science · doi:10.1007/978-3-319-54184-6_6 · Cited by 537 · cited 1×
“In 2016, researchers proposed a novel end-to-end trained model for visual speech recognition [19] and approach to construct large AV datasets suitable for AV-ASR [20].”
Cited by
Automatic Speech Recognition: A Survey
Malik, M., Malik, M. K., Mehmood, K., & Makhdoom, I. (2021) · Multimedia Tools and Applications · doi:10.1007/s11042-020-10073-7 · Cited by 358
“CDHMM can be further improved by using the large margin classifiers in the training process.”
BackgroundMethodInfluentialDeep learning for visual speech analysis: A survey
Sheng, C., Kuang, G., Bai, L., Hou, C., Guo, Y., Xu, X., Pietikäinen, M., & Liu, L. (2024) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2024.3376710 · Cited by 64
“[147] ST-CNN RNN-T (BiLSTM) seq2seq loss YT-31khrs √ character 33.”
Erdem, E., Kuyu, M., Yagcioglu, S., Frank, A., Parcalabescu, L., Plank, B., Babii, A., Turuta, O., Erdem, A., Calixto, I., et al. (2022) · Journal of Artificial Intelligence Research · doi:10.1613/jair.1.12918 · Cited by 54
Dimitri, G. M. (2022) · Computers · doi:10.3390/computers11110163 · Cited by 22
Cross-Modal Mutual Learning for Audio-Visual Speech Recognition and Manipulation
Yang, C.-C., Fan, W.-C., Yang, C.-F., & Wang, Y.-C. F. (2022) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v36i3.20210 · Cited by 16
“As for sentence-level speech recognition, previous works (Afouras et al. 2018; Chan et al. 2016; Garcia et al. 2019; Zhang, Cheng, and Wang 2019) aim at recognizing the character or word sequence in a full sentence by sequence-to-sequence learning.”
Result
Metadata
- Authors
- Makino, T., Liao, H., Assael, Y., Shillingford, B., Garcia, B., Braga, O., & Siohan, O.
- Venue
- 2019 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)
- Publisher
- IEEE
- Published
- 2019-12
- Pages
- 905-912
- OpenAlex
- W3006974783
- Cited by
- 129
- References
- 9
- FWCI
- 4.91
- Type
- conference paper
- Language
- en
- Open access
- green
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
How to cite
Cite CoChat for the checks on this page, and the paper for its own findings.
- This page
- CoChat. (2026). Citation check: Recurrent Neural Network Transducer for Audio-Visual Speech Recognition. https://app.cochat.ai/papers/10.1109/asru46091.2019.9004036
- The paper
- Makino, T., Liao, H., Assael, Y., Shillingford, B., Garcia, B., Braga, O., & Siohan, O. (2019). Recurrent Neural Network Transducer for Audio-Visual Speech Recognition. 2019 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU). https://doi.org/10.1109/asru46091.2019.9004036
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.