Analysis and Combination of Forward and Backward based Decoders for Improved Speech Transcription - Archive ouverte HAL Access content directly
Conference Papers Year : 2013

Analysis and Combination of Forward and Backward based Decoders for Improved Speech Transcription

(1) , (1)
1
Denis Jouvet
Dominique Fohr

Abstract

This paper analysis the behavior of forward and backward-based decoders used for speech transcription. Experiments have showed that backwardbased decoding leads to similar recognition performance as forward-based decoding, which is consistent with the fact that both systems handle similar information through the acoustic, lexical and language models. However, because of heuristics, search algorithms used in decoding explore only a limited portion of the search space. As forward-based and backward-based approaches do not process the speech signal in the same temporal way, they explore different portions of the search space; leading to complementary systems that can be efficiently combined using the ROVER approach. The speech transcription results achieved by combining forward-based and backward-based systems are significantly better than the results obtained by combining the same amount of forward-only or backward-only systems. This confirms the complementary of the forward and backward approaches and thus the usefulness of their combination.
Not file

Dates and versions

hal-00834296 , version 1 (14-06-2013)

Identifiers

  • HAL Id : hal-00834296 , version 1

Cite

Denis Jouvet, Dominique Fohr. Analysis and Combination of Forward and Backward based Decoders for Improved Speech Transcription. TSD - 16th International Conference on Text, Speech and Dialogue - 2013, Sep 2013, Pilsen, Czech Republic. pp.84-91. ⟨hal-00834296⟩
141 View
0 Download

Share

Gmail Facebook Twitter LinkedIn More