Statistical Adaptation of Acoustic Models to Noise Conditions for Robust Speech Recognition - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Conference Papers Year : 2002

Statistical Adaptation of Acoustic Models to Noise Conditions for Robust Speech Recognition

Abstract

Noise degrades the performance of Automatic Speech Recognition (ASR) systems working in real condition. The mismatch between the training and recognition conditions is considered the main factor involved in this degradation, and most methods for robust ASR are focussed on its minimization. In this work, we compare robust methods for ASR based on (a) the compensation of the noise effects and (b) the adaptation of the acoustic models to noise con-ditions. We propose a method for the adaptation of the acoustic models to the noise conditions based on a statistical formulation. In this method, each Gaussian is adapted to the noisy environment according to the estimated noise conditions. Recognition experiments have been carried out using speech acquired in real car environments. The results show the statistical formulation for adaptation provides an accurate method for robust ASR.
Not file

Dates and versions

inria-00100832 , version 1 (26-09-2006)

Identifiers

  • HAL Id : inria-00100832 , version 1

Cite

Angel de La Torre, Dominique Fohr, Jean-Paul Haton. Statistical Adaptation of Acoustic Models to Noise Conditions for Robust Speech Recognition. International Conference on Spoken Language Processing - ICSLP 2002, 2002, Denver, USA, pp.1437-1440. ⟨inria-00100832⟩
131 View
0 Download

Share

Gmail Facebook Twitter LinkedIn More