Adaptive Multimodal Fusion by Uncertainty Compensation With Application to Audiovisual Speech Recognition
Open accessThe DOI matches its Crossref record; 5 of the 5 references it cites were found in a registry or an index.
Abstract
While the accuracy of feature measurements heavily depends on changing environmental conditions, studying the consequences of this fact in pattern recognition tasks has received relatively little attention to date. In this paper, we explicitly take feature measurement uncertainty into account and show how multimodal classification and learning rules should be adjusted to compensate for its effects. Our approach is particularly fruitful in multimodal fusion scenarios, such as audiovisual speech recognition, where multiple streams of complementary time-evolving features are integrated. For such applications, provided that the measurement noise uncertainty for each feature stream can be estimated, the proposed framework leads to highly adaptive multimodal fusion rules which are easy and efficient to implement. Our technique is widely applicable and can be transparently integrated with either synchronous or asynchronous multimodal sequence integration architectures. We further show that multimodal fusion methods relying on stream weights can naturally emerge from our scheme under certain assumptions; this connection provides valuable insights into the adaptivity properties of our multimodal uncertainty compensation approach. We show how these ideas can be practically applied for audiovisual speech recognition. In this context, we propose improved techniques for person-independent visual feature extraction and uncertainty estimation with active appearance models, and also discuss how enhanced audio features along with their uncertainty estimates can be effectively computed. We demonstrate the efficacy of our approach in audiovisual speech recognition experiments on the CUAVE database using either synchronous or asynchronous multimodal integration models.
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
Hearing lips and seeing voices
MCGURK, H., & MACDONALD, J. (1976) · Nature · doi:10.1038/264746a0 · Cited by 6,183
Cootes, T. F., Edwards, G. J., & Taylor, C. J. (2001) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/34.927467 · Cited by 5,409
Maximum mutual information estimation of hidden Markov model parameters for speech recognition
Bahl, L., Brown, P., de Souza, P., & Mercer, R. (2005) · ICASSP '86. IEEE International Conference on Acoustics, Speech, and Signal Processing · doi:10.1109/icassp.1986.1169179 · Cited by 817 · cited 1×
“The importance of discriminative approaches to audio-only ASR has been highlighted by the success of discriminative model training techniques using the maximum mutual information [35] or the minimum classification error rate”
MethodSome statistical issues in the comparison of speech recognition algorithms
Gillick, L., & Cox, S. J. (2003) · International Conference on Acoustics, Speech, and Signal Processing · doi:10.1109/icassp.1989.266481 · Cited by 636
Audio-visual speech modeling for continuous speech recognition
Dupont, S., & Luettin, J. (2000) · IEEE Transactions on Multimedia · doi:10.1109/6046.865479 · Cited by 598
Cited by
Deep Learning: Methods and Applications
Deng, L., & Yu, D. (2014) · Foundations and Trends® in Signal Processing · doi:10.1561/2000000039 · Cited by 3,480
“However, the same paper also shows that a model of [278] in which a sophisticated signal processing technique for extracting visual features, together with the uncertainty-compensation method developed originally from robust speech recognition [104], gives the best classification accuracy in the cross-modal learning t…”
Method(2011) · Cited by 2,752
Deep Learning: Methods and Applications
Deng, L. (2014) · now publishers, Inc. eBooks · doi:10.1561/9781601988157 · Cited by 1,759
A tutorial survey of architectures, algorithms, and applications for deep learning
Deng, L. (2014) · APSIPA Transactions on Signal and Information Processing · doi:10.1017/atsip.2013.9 · Cited by 725
Chung, J. S., & Zisserman, A. (2017) · Lecture Notes in Computer Science · doi:10.1007/978-3-319-54184-6_6 · Cited by 537
Metadata
- Authors
- Papandreou, G., Katsamanis, A., Pitsikalis, V., & Maragos, P.
- Venue
- IEEE Transactions on Audio, Speech, and Language Processing
- Published
- 2009-03
- Volume
- 17
- Issue
- 3
- Pages
- 423-435
- ISSN
- 1558-7916 (ISSN-L)
- OpenAlex
- W2142075667
- Cited by
- 101
- References
- 5
- FWCI
- 8.55
- Type
- journal article
- 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: Adaptive Multimodal Fusion by Uncertainty Compensation With Application to Audiovisual Speech Recognition. https://app.cochat.ai/papers/10.1109/tasl.2008.2011515
- The paper
- Papandreou, G., Katsamanis, A., Pitsikalis, V., & Maragos, P. (2009). Adaptive Multimodal Fusion by Uncertainty Compensation With Application to Audiovisual Speech Recognition. IEEE Transactions on Audio, Speech, and Language Processing. https://doi.org/10.1109/tasl.2008.2011515
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.