Audio-Visual Automatic Speech Recognition: An Overview
By Gerasimos Potamianos, Chalapathy Neti, Juergen Luettin, Iain Matthews. 2004
408 citations recorded by the source corpus.
View Paper: https://www.semanticscholar.org/paper/4f3656da4cbd1979a5fa763f90defa1f90d53583
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
- Yoshua Bengio
- Quoc V. Le
- Bo Li
- Sergey Levine
- Dacheng Tao
- Andrew Zisserman
- Ruslan Salakhutdinov
- Trevor Darrell
Citations in the corpus
- Partial Multi-View Clustering (2014, methodology): “In speech recognition, the audio and visual sources are used together as two sources (Ngiam et al. 2011; Potamianos et al. 2004).”
- Large-Scale Visual Speech Recognition (2018, background): “For further details, we refer the reader to the survey material of [22, 29, 30].”
- Automatic analysis of multimodal group actions in meetings (2005, background): “An intermediate solution, which we call composite HMM, considers all combinations of states in the same action only [48].”
- Balanced Multimodal Learning via On-the-fly Gradient Modulation (2022, background): “, action recognition [10, 23, 29], audiovisual speech recognition [16, 33], and visual question answering [2, 19].”
- Combining Residual Networks with LSTMs for Lipreading (2017, methodology): “For an analytic review on traditional lipreading methods we refer to [17] and [18].”
- Distance based similarity models for content based multimedia retrieval (2013, methodology): “…instance automatic face expression analysis [Fasel and Luettin, 2003], gesture recognition [Marcel, 2002], human motion analysis [Aggarwal and Cai, 1999], or audio-visual automatic speech recognition [Potamianos et al., 2004] in order to capture the information needs more precisely and intuitively.”
- Multimodal Deep Learning (2011, methodology): “For the multimodal fusion setting, data from all modalities is available at all phases; this represents the typical setting considered in most prior work in audio-visual speech recognition [3].”
- Multimodal Human Computer Interaction: A Survey (2005, methodology): “More details about this approach can be found in [143].”