Masato Mimura, Shinsuke Sakai, Tatsuya Kawahara. Joint Optimization of Denoising Autoencoder and DNN Acoustic Model Based on Multi-Target Learning for Noisy Speech Recognition. In Nelson Morgan, editor, Interspeech 2016, 17th Annual Conference of the International Speech Communication Association, San Francisco, CA, USA, September 8-12, 2016. pages 3803-3807, ISCA, 2016. [doi]
Abstract is missing.