Monotonic segmental attention for automatic speech recognition

RWTH Publications (RWTH Aachen)

Abstract

We introduce a novel segmental-attention model for automatic speech recognition. We restrict the decoder attention to segments to avoid quadratic runtime of global attention, better generalize to long sequences, and eventually enable streaming. We directly compare global-attention and different segmental-attention modeling variants. We develop and compare two separate time-synchronous decoders, one specifically taking the segmental nature into account, yielding further improvements. Using time-synchronous decoding for segmental models is novel and a step towards streaming applications. Our experiments show the importance of a length model to predict the segment boundaries. The final best segmental-attention model using segmental decoding performs better than global-attention, in contrast to other monotonic attention approaches in the literature. Further, we observe that the segmental model generalizes much better to long sequences of up to several minutes.

Authors 4

1. Robin Schmitt Aachen AppTek GmbH Human Language Technology and Pattern Recognition Computer Science Department

   RWTH Aachen University · FH Aachen

   Affiliation as printed

   AppTek GmbH , 52062 Aachen , Germany

   Human Language Technology and Pattern Recognition , Computer Science Department , RWTH Aachen University , 52062 Aachen , Germany,

2. Wei Guo Zhou Aachen AppTek GmbH Human Language Technology and Pattern Recognition Computer Science Department

   RWTH Aachen University · FH Aachen

   Affiliation as printed

   AppTek GmbH , 52062 Aachen , Germany

   Human Language Technology and Pattern Recognition , Computer Science Department , RWTH Aachen University , 52062 Aachen , Germany,

3. Ralf Schlüter
4. Hermann Ney Aachen AppTek GmbH Human Language Technology and Pattern Recognition Computer Science Department

   RWTH Aachen University · FH Aachen

   Affiliation as printed

   AppTek GmbH , 52062 Aachen , Germany

   Human Language Technology and Pattern Recognition , Computer Science Department , RWTH Aachen University , 52062 Aachen , Germany,