Efficient Sequence Training of Attention Models using Approximative Recombination

arXiv (Cornell University)

Abstract

Sequence discriminative training is a great tool to improve the performance of an automatic speech recognition system. It does, however, necessitate a sum over all possible word sequences, which is intractable to compute in practice. Current state-of-the-art systems with unlimited label context circumvent this problem by limiting the summation to an n-best list of relevant competing hypotheses obtained from beam search. This work proposes to perform (approximative) recombinations of hypotheses during beam search, if they share a common local history. The error that is incurred by the approximation is analyzed and it is shown that using this technique the effective beam size can be increased by several orders of magnitude without significantly increasing the computational requirements. Lastly, it is shown that this technique can be used to effectively perform sequence discriminative training for attention-based encoder-decoder acoustic models on the LibriSpeech task.

Authors 5

1. Nils-Philipp Wynands Aachen Human Language Technology and Pattern Recognition Computer Science Department

   RWTH Aachen University

   Affiliation as printed

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

2. Wilfried Michel 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. Jan Rosendahl Aachen Human Language Technology and Pattern Recognition Computer Science Department

   RWTH Aachen University

   Affiliation as printed

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

4. Ralf Schlüter
5. 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,