Deep complementary bottleneck features for visual speech recognition
Open accessThe DOI matches its Crossref record; 1 of the 1 references it cites were found in a registry or an index.
Abstract
Deep bottleneck features (DBNFs) have been used successfully in the past for acoustic speech recognition from audio. However, research on extracting DBNFs for visual speech recognition is very limited. In this work, we present an approach to extract deep bottleneck visual features based on deep autoencoders. To the best of our knowledge, this is the first work that extracts DBNFs for visual speech recognition directly from pixels. We first train a deep autoencoder with a bottleneck layer in order to reduce the dimensionality of the image. Then the autoencoder's decoding layers are replaced by classification layers which make the bottleneck features more discriminative. Discrete Cosine Transform (DCT) features are also appended in the bottleneck layer during training in order to make the bottleneck features complementary to DCT features. Long-Short Term Memory (LSTM) networks are used to model the temporal dynamics and the performance is evaluated on the OuluVS and AVLetters databases. The extracted complementary DBNF in combination with DCT features achieve the best performance resulting in an absolute improvement of up to 5% over the DCT baseline.
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
A Practical Guide to Training Restricted Boltzmann Machines
Hinton, G. E. (2012) · Lecture Notes in Computer Science · doi:10.1007/978-3-642-35289-8_32 · Cited by 2,852 · cited 1×
“The OuluVS contains 20 speakers saying 10 utterances, 5 times each, so in total there 100 examples per utterance.”
Background
Cited by
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
Chung, J. S., & Zisserman, A. (2017) · Lecture Notes in Computer Science · doi:10.1007/978-3-319-54184-6_6 · Cited by 537
“It is worth noting that the top-1 classification accuracy of 65%, shown in Table 4, is comparable to that of many of the recent works [7, 24, 29] performed on lexicon sizes that are orders of magnitude smaller (Table 1).”
MethodResultCombining Residual Networks with LSTMs for Lipreading
Stafylakis, T., & Tzimiropoulos, G. (2017) · Interspeech 2017 · doi:10.21437/interspeech.2017-85 · Cited by 348
“In [23], bottleneck features are extracted using Deep Autoencoder.”
MethodEnd-to-End Audiovisual Speech Recognition
Petridis, S., Stafylakis, T., Ma, P., Cai, F., Tzimiropoulos, G., & Pantic, M. (2018) · 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) · doi:10.1109/icassp.2018.8461326 · Cited by 289
Self-citationLipreading Using Temporal Convolutional Networks
Martinez, B., Ma, P., Petridis, S., & Pantic, M. (2020) · ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) · doi:10.1109/icassp40776.2020.9053841 · Cited by 276
Self-citation
Metadata
- Authors
- Petridis, S., & Pantic, M.
- Venue
- 2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
- Publisher
- IEEE
- Published
- 2016-03
- Pages
- 2304-2308
- ISSN
- 1520-6149 (ISSN-L)
- OpenAlex
- W2404704342
- Cited by
- 112
- References
- 1
- FWCI
- 13.65
- 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: Deep complementary bottleneck features for visual speech recognition. https://app.cochat.ai/papers/10.1109/icassp.2016.7472088
- The paper
- Petridis, S., & Pantic, M. (2016). Deep complementary bottleneck features for visual speech recognition. 2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). https://doi.org/10.1109/icassp.2016.7472088
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.