Class-based speech recognition using a maximum dissimilarity criterion and a tolerance classification margin - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Conference Papers Year : 2012

Class-based speech recognition using a maximum dissimilarity criterion and a tolerance classification margin

Arseniy Gorin
  • Function : Author
  • PersonId : 767294
  • IdRef : 182505596
Denis Jouvet

Abstract

One of the difficult problems of Automatic Speech Recognition (ASR) is dealing with the acoustic signal variability. Much state-of-the-art research has demonstrated that splitting data into classes and using a model specific to each class provides better results. However, when the dataset is not large enough and the number of classes increases, there is less data for adapting the class models and the performance degrades. This work extends and combines previous research on unsupervised splits of datasets to build maximally separated classes and the introduction of a tolerance classification margin for a better training of the class model parameters. Experiments, carried out on the French radio broadcast ESTER2 data, show an improvement in recognition results compared to the ones obtained previously. Finally, we demonstrate that combining the decoding results from different class models leads to even more significant improvements.
No file

Dates and versions

hal-00753454 , version 1 (19-11-2012)

Identifiers

  • HAL Id : hal-00753454 , version 1

Cite

Arseniy Gorin, Denis Jouvet. Class-based speech recognition using a maximum dissimilarity criterion and a tolerance classification margin. SLT 2012 - 4th IEEE Workshop on Spoken Language Technology, Dec 2012, Miami, United States. ⟨hal-00753454⟩
114 View
0 Download

Share

Gmail Facebook X LinkedIn More