TY - CONF T1 - Improving audio-visual speech recognition using deep neural networks with dynamic stream reliability estimates JO - Proceedings of the 2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP 2017) UR - https://eprints.whiterose.ac.uk/id/eprint/121254 UR - https://doi.org/10.1109/ICASSP.2017.7953172 PY - 2017/06/19 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 SN - 9781509041176 SP - 5320 EP - 5324 Y2 - 2025/11/04 ER -