Multi-level adaptive networks in tandem and hybrid ASR systems

Peter Bell, Pawel Swietojanski, Steve RenalsICASSP 2013 · OpenReview

Abstract

In this paper we investigate the use of Multi-level adaptive networks (MLAN) to incorporate out-of-domain data when training large vocabulary speech recognition systems. In a set of experiments on multi-genre broadcast data and on TED lecture recordings we present results using of out-of-domain features in a hybrid DNN system and explore tandem systems using a variety of input acoustic features. Our experiments indicate using the MLAN approach in both hybrid and tandem systems results in consistent reductions in word error rate of 5-10% relative.
BibTeX
@inproceedings{bell2013multi,
  author = {Peter Bell and Pawel Swietojanski and Steve Renals},
  title = {{Multi-level adaptive networks in tandem and hybrid ASR systems}},
  booktitle = {IEEE International Conference on Acoustics, Speech and Signal Processing},
  year = {2013},
  url = {https://openreview.net/forum?id=FoENTb4uup},
}

Loading related content...

Figure