An investigation of likelihood normalization for robust ASRReport as inadecuate




An investigation of likelihood normalization for robust ASR - Download this document for free, or read online. Document in PDF available to download.

1 PAROLE - Analysis, perception and recognition of speech Inria Nancy - Grand Est, LORIA - NLPKD - Department of Natural Language Processing & Knowledge Discovery 2 ILSP - Institute for Language and Speech Processing 3 OFAI - Austrian Research Institute for Artificial Intelligence

Abstract : Noise-robust automatic speech recognition ASR systems rely on feature and-or model compensation. Existing compensation techniques typically operate on the features or on the parameters of the acoustic models themselves. By contrast, a number of normalization techniques have been defined in the field of speaker verification that operate on the resulting log-likelihood scores. In this paper, we provide a theoretical motivation for likelihood normalization due to the so-called -hubness- phenomenon and we evaluate the benefit of several normalization techniques on ASR accuracy for the 2nd CHiME Challenge task. We show that symmetric normalization S-norm reduces the relative error rate by 43% alone and by 10% after feature and model compensation.





Author: Emmanuel Vincent - Aggelos Gkiokas - Dominik Schnitzer - Arthur Flexer -

Source: https://hal.archives-ouvertes.fr/



DOWNLOAD PDF




Related documents