TY - CONF T1 - Improving audio-visual speech recognition using deep neural networks with dynamic stream reliability estimates JO - 2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) UR - http://eprints.whiterose.ac.uk/121254/ PY - 2017/06/16 AU - Meutzner H AU - Ma N AU - Nickel R AU - Schymura C AU - Kolossa D ED - DO - DOI: 10.1109/icassp.2017.7953172 PB - IEEE Y2 - 2024/10/19 ER -