Audio Segmentation for Robust Real-Time Speech Recognition Based on Neural Networks

Audio Segmentation for Robust Real-Time Speech Recognition Based on Neural Networks Micha Wetzel author Matthias Sperber author Alexander Waibel author 2016-dec 8-9 text Proceedings of the 13th International Conference on Spoken Language Translation Mauro Cettolo editor Jan Niehues editor Sebastian Stüker editor Luisa Bentivogli editor Rolando Cattoni editor Marcello Federico editor International Workshop on Spoken Language Translation Seattle, Washington D.C conference publication wetzel-etal-2016-audio https://aclanthology.org/2016.iwslt-1.4/ 2016-dec 8-9