Continuous digit recognition in noise: Reservoirs can do an excellent job!

Azarakhsh Jalalvand, Fabian Triefenbach, Jean Pierre Martens

Research output: Chapter in Book/Report/Conference proceedingConference contribution

5 Scopus citations

Abstract

In this paper a formerly proposed continuous digit recognition system based on Reservoir Computing (RC) is improved in two respects: (1) the single reservoir is substituted by a stack of reservoirs, and (2) the straightforward mapping of reservoir outputs to state likelihoods is replaced by a trained non-parametric mapping. Furthermore, it is shown that a reservoir-based method can improve a model trained on clean speech to work better in a noisy condition from which it has a number of unknown digit string recordings available. The first two improvements have lead to a system that outperforms a HMM based system with the same noise robust features as input. The model adaptation offers a promising supplementary gain at modest noise levels.

Original languageEnglish (US)
Title of host publication13th Annual Conference of the International Speech Communication Association 2012, INTERSPEECH 2012
Pages1802-1805
Number of pages4
StatePublished - 2012
Externally publishedYes
Event13th Annual Conference of the International Speech Communication Association 2012, INTERSPEECH 2012 - Portland, OR, United States
Duration: Sep 9 2012Sep 13 2012

Publication series

Name13th Annual Conference of the International Speech Communication Association 2012, INTERSPEECH 2012
Volume3

Conference

Conference13th Annual Conference of the International Speech Communication Association 2012, INTERSPEECH 2012
Country/TerritoryUnited States
CityPortland, OR
Period9/9/129/13/12

All Science Journal Classification (ASJC) codes

  • Computer Networks and Communications
  • Communication

Keywords

  • Acoustic modeling
  • Model adaptation
  • Noise robustness
  • Reservoir computing

Fingerprint

Dive into the research topics of 'Continuous digit recognition in noise: Reservoirs can do an excellent job!'. Together they form a unique fingerprint.

Cite this