Towards Robust Waveform-Based Acoustic Models

Towards Robust Waveform-Based Acoustic Models

We study the problem of learning robust acoustic models in adverse environments, characterized by a significant mismatch between training and test conditions. This problem is of paramount importance for the deployment of speech recognition systems that need to perform well in unseen environments. Fi...

Full description

Bibliographic Details
Main Authors: Cvetkovic, Z. (Author), Oglic, D. (Author), Renals, S. (Author), Sollich, P. (Author), Yu, B.G (Author)
Format: Article
Language:English
Published: Institute of Electrical and Electronics Engineers Inc. 2022
Subjects:
Acoustics
Acoustics model
data augmentation
Data augmentation
Delta functions
Extraction
Feature extraction
Features extraction
Generalisation
Mixtures
out-of-distribution generalization
Out-of-distribution generalization
Population statistics
Risk management
Risk minimization
Risks management
Sampling
Speech processing
Speech recognition
Standards
Testing
Training
vicinal risk minimization
Vicinal risk minimization
Waveform-based model
waveform-based models
Waveforms
Online Access:View Fulltext in Publisher

Internet

View Fulltext in Publisher

Similar Items