Towards Missing Data Recognition with Cepstral Features

Christophe Cerisara 1
1 PAROLE - Analysis, perception and recognition of speech
INRIA Lorraine, LORIA - Laboratoire Lorrain de Recherche en Informatique et ses Applications
Abstract : We study in this work the Missing Data Recognition (MDR) framework applied to a large vocabulary continuous speech recognition (LVCSR) task with cepstral models when the speech signal is corrupted by musical noise. We do not propose a full system that solves this difficult problem, but we rather present some of the issues involved and study some possible solutions to them. We focus in this work on the issues concerning the application of masks to cepstral models. We further identify possible errors and study how some of them affect the performances of the system.
Document type :
Conference papers
Complete list of metadatas

Cited literature [8 references]  Display  Hide  Download

https://hal.inria.fr/inria-00107648
Contributor : Publications Loria <>
Submitted on : Thursday, October 19, 2006 - 9:03:59 AM
Last modification on : Tuesday, September 24, 2019 - 4:00:13 PM
Long-term archiving on : Wednesday, March 29, 2017 - 1:00:40 PM

Identifiers

  • HAL Id : inria-00107648, version 1

Collections

Citation

Christophe Cerisara. Towards Missing Data Recognition with Cepstral Features. 8th European Conference on Speech Communication and Technology - EUROSPEECH'03, Sep 2003, Geneva, Switzerland, 4 p. ⟨inria-00107648⟩

Share

Metrics

Record views

249

Files downloads

197