Robust automatic speech recognition with missing and unreliable acoustic data

DOI10.1016/S0167-6393(00)00034-0MaRDI QIDQ4794937zbMATH OpenOpenAlexFDO

Authors Martin Cooke, Phil Green, Ljubomir Josifovski, Ascension Vizinho

Publication date 20 February 2003

Published in Speech Communication (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1016/s0167-6393(00)00034-0

zbMATH Keywords

HMMmissing dataspectral subtractiondata imputationrobust ASR

Mathematics Subject Classification ID

Pattern recognition, speech recognition (68T10) Computing methodologies and applications (68U99)

Recommendations

• Acoustic backing-off as an implementation of missing feature theory
• Spectral reconstruction and noise model estimation based on a masking model for noise robust speech recognition
• Automatic Speech Recognition Using Missing Data Techniques: Handling of Real-World Data
• Use of missing and unreliable data for audiovisual speech recognition
• Acoustic features and distance measure to reduce vulnerability of ASR performance due to the presence of communication channel and/or background noise

Cited in

(20)

• Mixtures of common factor analyzers for high-dimensional data with missing information
• Likelihood-maximizing-based multiband spectral subtraction for robust speech recognition
• Techniques for dealing with incomplete data: a tutorial and survey
• Multi-stream adaptive evidence combination for noise robust ASR
• Acoustic backing-off as an implementation of missing feature theory
• Hidden Markov model with missing emissions
• Robust speech recognition using factorial HMMs for home environments
• Automatic Speech Recognition Using Missing Data Techniques: Handling of Real-World Data
• Evidence Modeling for Missing Data Speech Recognition Using Small Microphone Arrays
• Missing data imputation through GTM as a mixture of \(t\)-distributions
• Acoustic features and distance measure to reduce vulnerability of ASR performance due to the presence of communication channel and/or background noise
• Noise-robust speech recognition through auditory feature detection and spike sequence decoding
• On classification with missing data using rough-neuro-fuzzy systems
• Neuro-rough-fuzzy approach for regression modelling from missing data
• A novel fuzzy clustering algorithm using observation weighting and context information for reverberant blind speech separation
• Spectral reconstruction and noise model estimation based on a masking model for noise robust speech recognition
• Discrimination of homographs distorted by a lengthy impulsive noise
• Reconstructing noise-corrupted spectrographic components for robust speech recognition
• Use of missing and unreliable data for audiovisual speech recognition
• Rough subspace neuro-fuzzy system

This page was built for publication: Robust automatic speech recognition with missing and unreliable acoustic data

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q4794937)