Deep Bidirectional Long Short-Term Memory Recurrent Neural Networks for Grapheme-to-Phoneme Conversion Utilizing Complex Many-to-Many Alignments

Amr El-Desoky Mousa, Björn W. Schuller. Deep Bidirectional Long Short-Term Memory Recurrent Neural Networks for Grapheme-to-Phoneme Conversion Utilizing Complex Many-to-Many Alignments. In Nelson Morgan, editor, Interspeech 2016, 17th Annual Conference of the International Speech Communication Association, San Francisco, CA, USA, September 8-12, 2016. pages 2836-2840, ISCA, 2016. [doi]

Abstract

Abstract is missing.