A Data Driven Approach to Audiovisual Speech Mapping
| Autor: | Amir Hussain, Peter Derleth, Jon Barker, Roger Watt, Andrew Abel, Ricard Marxer, Bill Whitmer |
|---|---|
| Přispěvatelé: | Liu, Cheng-Lin, Hussain, Amir, Luo, Bin, Tan, Kay Chen, Zeng, Yi, Zhang, Zhaoxiang |
| Rok vydání: | 2016 |
| Předmět: |
Speech Acoustics
Computer science Speech recognition Frame (networking) Speech technology Speech corpus 02 engineering and technology Viseme Speech processing Filter bank 01 natural sciences Data-driven 0103 physical sciences 0202 electrical engineering electronic engineering information engineering 020201 artificial intelligence & image processing 010301 acoustics |
| Zdroj: | Advances in Brain Inspired Cognitive Systems ISBN: 9783319496849 BICS |
| ISSN: | 0302-9743 |
| DOI: | 10.1007/978-3-319-49685-6_30 |
| Popis: | The concept of using visual information as part of audio speech processing has been of significant recent interest. This paper presents a data driven approach that considers estimating audio speech acoustics using only temporal visual information without considering linguistic features such as phonemes and visemes. Audio (log filterbank) and visual (2D-DCT) features are extracted, and various configurations of MLP and datasets are used to identify optimal results, showing that given a sequence of prior visual frames an equivalent reasonably accurate audio frame estimation can be mapped. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|