5th International Conference on Spoken Language Processing

Sydney, Australia
November 30 - December 4, 1998

Interfacing of CASA and Partial Recognition Based on a Multistream Technique

Frédéric Berthommier (1), Hervé Glotin (2), Emmanuel Tessier (1), Hervé Bourlard (2)

(1) ICP, France
(2) IDIAP, Switzerland

We propose a running demonstration of coupling between an intermediate processing step (named CASA), based on the harmonicity cue, and partial recognition, implemented with a HMM/ANN multistream technique [2]. The model is able to recognise words corrupted with narrow band noise, either stationary or having variable center frequency. The principle is to identify frame by frame the most noisy subband within four subbands by analysing a SNR-dependent representation. A static partial recogniser is fed with the remaining subbands. We establish on Numbers93 the noisy-band identification (NBI) performance as well as the word error rate (WER), and alter the correlation between these two indexes by changing the distribution of the noise.

Full Paper

Bibliographic reference.  Berthommier, Frédéric / Glotin, Hervé / Tessier, Emmanuel / Bourlard, Hervé (1998): "Interfacing of CASA and partial recognition based on a multistream technique", In ICSLP-1998, paper 0600.