Yusuke Fujita, Ryoichi Takashima, Takeshi Homma, Masahito Togami. Data Augmentation Using Multi-Input Multi-Output Source Separation for Deep Neural Network Based Acoustic Modeling. In Nelson Morgan, editor, Interspeech 2016, 17th Annual Conference of the International Speech Communication Association, San Francisco, CA, USA, September 8-12, 2016. pages 3818-3822, ISCA, 2016. [doi]
Abstract is missing.