English

Latent Sequence Decompositions

Machine Learning 2017-02-08 v6 Computation and Language Machine Learning

Abstract

We present the Latent Sequence Decompositions (LSD) framework. LSD decomposes sequences with variable lengthed output units as a function of both the input sequence and the output sequence. We present a training algorithm which samples valid extensions and an approximate decoding algorithm. We experiment with the Wall Street Journal speech recognition task. Our LSD model achieves 12.9% WER compared to a character baseline of 14.8% WER. When combined with a convolutional network on the encoder, we achieve 9.6% WER.

Keywords

Cite

@article{arxiv.1610.03035,
  title  = {Latent Sequence Decompositions},
  author = {William Chan and Yu Zhang and Quoc Le and Navdeep Jaitly},
  journal= {arXiv preprint arXiv:1610.03035},
  year   = {2017}
}
R2 v1 2026-06-22T16:16:45.732Z