Exploring ROI size in deep learning based lipreading
The DOI matches its Crossref record; 37 of the 39 references it cites were found in a registry or an index.
Abstract
Automatic speechreading systems have increasingly exploited deep learning advances, resulting in dramatic gains over traditional methods. State-of-the-art systems typically employ convolutional neural networks (CNNs), operating on a video region-of-interest (ROI) that contains the speaker’s mouth. However, little or no attention has been paid to the effects of ROI physical coverage and resolution on the resulting recognition performance within the deep learning framework. In this paper, we investigate such choices for a visual-only speech recognition system based on CNNs and long short-term memory models that we present in detail. Further, we employ a separate CNN to perform face detection and facial landmark localization, driving the ROI extraction process. We conduct experiments on a multi-speaker corpus of connected digits utterances, recorded in ideal visual conditions. Our results show that ROI design choices affect automatic speechreading performance significantly: the best visual-only word error rate (5.07%) corresponds to a ROI that contains a large part of the lower face, in addition to just the mouth, and at a relatively high resolution. Noticeably, the result represents a 27% relative error reduction compared to employing the entire lower face as the ROI. © 2017 14th International Conference on Auditory-Visual Speech Processing, AVSP 2017. All rights reserved.
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
“Koumparoulis et al . [121] proved that the selection of ROI will significantly affect the final recognition performance, but it is still unable to determine the optimal ROI.”
From Deep learning for visual speech analysis: A survey (2024) · cites this paper as [121]
Citations
Cites
Hochreiter, S., & Schmidhuber, J. (1997) · Neural Computation · doi:10.1162/neco.1997.9.8.1735 · Cited by 102,318
(2014) · Cited by 33,419
Girshick, R. (2015) · 2015 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2015.169 · Cited by 28,105
Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification
He, K., Zhang, X., Ren, S., & Sun, J. (2015) · 2015 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2015.123 · Cited by 19,741
Sequence to Sequence Learning with Neural Networks
Sutskever, I., Vinyals, O., & Le, Q. V. (2014) · arXiv · doi:10.48550/arxiv.1409.3215 · Cited by 17,766
Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
Ioffe, S. (2024) · arXiv (Cornell University) · doi:10.57702/o9raffed · Cited by 14,214
(2010) · Cited by 8,261
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
(2011) · Cited by 2,752
Towards End-To-End Speech Recognition with Recurrent Neural Networks
Graves, A., & Jaitly, N. (2014) · Cited by 2,557
Cited by
Large-Scale Visual Speech Recognition
Shillingford, B., Assael, Y., Hoffman, M. W., Paine, T., Hughes, C., Prabhu, U., Liao, H., Sak, H., Rao, K., Bennett, L., et al. (2019) · Interspeech 2019 · doi:10.21437/interspeech.2019-1669 · Cited by 154
Sub-word Level Lip Reading With Visual Attention
Prajwal, K. R., Afouras, T., & Zisserman, A. (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/cvpr52688.2022.00510 · Cited by 164
Can We Read Speech Beyond the Lips? Rethinking RoI Selection for Deep Visual Speech Recognition
Zhang, Y., Yang, S., Xiao, J., Shan, S., & Chen, X. (2020) · International Conference on Automatic Face and Gesture Recognition · doi:10.1109/fg47880.2020.00134 · Cited by 105
RFID Tattoo: A Wireless Platform for Speech Recognition
Wang, J., Pan, C., Jin, H., Singh, V. K., Jain, Y., Hong, J., Majidi, C., & Kumar, S. (2019) · Proceedings of the ACM on Interactive Mobile Wearable and Ubiquitous Technologies · doi:10.1145/3369812 · Cited by 73
Zhang, R., Li, K., Hao, Y., Wang, Y., Lai, Z., Guimbretière, F. V., & Zhang, C. (2023) · CHI Conference on Human Factors in Computing Systems · doi:10.1145/3544548.3580801 · Cited by 71
Metadata
- Authors
- Koumparoulis, A., Potamianos, G., Mroueh, Y., & Rennie, S. J.
- Venue
- The 14th International Conference on Auditory-Visual Speech Processing
- Publisher
- ISCA
- Published
- 2017-08-25
- Pages
- 64-69
- OpenAlex
- W2891226622
- Cited by
- 21
- References
- 39
- Citations by year
- 2025: 2 · 2024: 2 · 2023: 1 · 2022: 2 · 2021: 2 · 2020: 3 · 2019: 2 · 2018: 7
- FWCI
- 2.33
- Type
- conference paper
- Language
- en
- Open access
- closed
- Locations
- International Conference on Auditory-Visual Speech Processing (AVSP) (publishedVersion)
- University of Thessaly Institutional Repository (University of Thessaly) (submittedVersion)
- Topics
- Physical Sciences › Computer Science › Signal Processing › Speech and Audio Processing
- Physical Sciences › Computer Science › Artificial Intelligence › Speech Recognition and Synthesis
- Physical Sciences › Computer Science › Human-Computer Interaction › Hand Gesture Recognition Systems
- Keywords
- lip reading, region of interest size, convolutional neural networks, long short-term memory, face detection, facial landmark detection, oral region, connected digits, 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
How to cite
Cite CoChat for the checks on this page, and the paper for its own findings.
- This page
- CoChat. (2026). Citation check: Exploring ROI size in deep learning based lipreading. https://app.cochat.ai/papers/10.21437/avsp.2017-13
- The paper
- Koumparoulis, A., Potamianos, G., Mroueh, Y., & Rennie, S. J. (2017). Exploring ROI size in deep learning based lipreading. The 14th International Conference on Auditory-Visual Speech Processing. https://doi.org/10.21437/avsp.2017-13
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.