Feature Frame Stacking in RNN-Based Tandem ASR Systems - Learned vs. Predefined Context

Martin Wöllmer, Björn Schuller, Gerhard Rigoll. Feature Frame Stacking in RNN-Based Tandem ASR Systems - Learned vs. Predefined Context. In INTERSPEECH 2011, 12th Annual Conference of the International Speech Communication Association, Florence, Italy, August 27-31, 2011. pages 1233-1236, ISCA, 2011. [doi]

Abstract

Abstract is missing.