Data Augmentation for Training of Noise Robust Acoustic Models

Communications in Computer and Information Science - Analysis of Images, Social Networks and Texts ◽

10.1007/978-3-319-52920-2_2 ◽

2017 ◽

pp. 17-25 ◽

Author(s):

Tatiana Prisyach ◽

Valentin Mendelev ◽

Dmitry Ubskiy

Keyword(s):

Data Augmentation ◽

Acoustic Models ◽

Download Full-text

A Perceptually Inspired Data Augmentation Method for Noise Robust CNN Acoustic Models

Speech and Computer - Lecture Notes in Computer Science ◽

10.1007/978-3-319-99579-3_71 ◽

2018 ◽

pp. 697-706 ◽

Author(s):

László Tóth ◽

György Kovács ◽

Dirk Van Compernolle

Keyword(s):

Data Augmentation ◽

Acoustic Models ◽

Download Full-text

Noise Robust Automatic Scoring Based on Deep Neural Network Acoustic Models with Lattice-Free MMI and Factorized Adaptation

Mobile Networks and Applications ◽

10.1007/s11036-021-01878-3 ◽

2021 ◽

Author(s):

Dean Luo ◽

Linzhong Xia ◽

Mingxiang Guan

Keyword(s):

Neural Network ◽

Deep Neural Network ◽

Acoustic Models ◽

Noise Robust ◽

Automatic Scoring

Download Full-text

Transliteration Based Data Augmentation for Training Multilingual ASR Acoustic Models in Low Resource Settings

10.21437/interspeech.2020-2593 ◽

2020 ◽

Author(s):

Samuel Thomas ◽

Kartik Audhkhasi ◽

Brian Kingsbury

Keyword(s):

Data Augmentation ◽

Low Resource Settings ◽

Acoustic Models ◽

Download Full-text

In domain training data augmentation on noise robust Punjabi Children speech recognition

Journal of Ambient Intelligence and Humanized Computing ◽

10.1007/s12652-021-03468-3 ◽

2021 ◽

Author(s):

Virender Kadyan ◽

Puneet Bawa ◽

Taniya Hasija

Keyword(s):

Speech Recognition ◽

Data Augmentation ◽

Training Data ◽

Noise Robust ◽

Children Speech

Download Full-text

Generative Adversarial Networks Based Data Augmentation for Noise Robust Speech Recognition

2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) ◽

10.1109/icassp.2018.8462624 ◽

2018 ◽

Author(s):

Hu Hu ◽

Tian Tan ◽

Yanmin Qian

Keyword(s):

Speech Recognition ◽

Data Augmentation ◽

Generative Adversarial Networks ◽

Robust Speech Recognition ◽

Adversarial Networks ◽

Noise Robust Speech Recognition ◽

Download Full-text

Noise robust continuous digit recognition with reservoir-based acoustic models

2013 International Symposium on Intelligent Signal Processing and Communication Systems ◽

10.1109/ispacs.2013.6704547 ◽

2013 ◽

Author(s):

Azarakhsh Jalalvand ◽

Kris Demuynck ◽

Jean-Pierre Martens

Keyword(s):

Acoustic Models ◽

Digit Recognition ◽

Download Full-text

Data Augmentation Using Artificial Immune Systems For Noise-Robust CNN Models

2020 IEEE International Conference on Image Processing (ICIP) ◽

10.1109/icip40778.2020.9191116 ◽

2020 ◽

Author(s):

Mark Ofori-Oduro ◽

Maria A. Amer

Keyword(s):

Data Augmentation ◽

Artificial Immune Systems ◽

Artificial Immune ◽

Immune Systems ◽

Download Full-text

Mind wandering as data augmentation: How mental travel supports abstraction

Behavioral and Brain Sciences ◽

10.1017/s0140525x1900311x ◽

2020 ◽

Vol 43 ◽

Author(s):

Myrthe Faber

Keyword(s):

Machine Learning ◽

Data Augmentation ◽

Mental Content ◽

Mind Wandering ◽

Theoretical Framework ◽

Important Addition

Abstract Gilead et al. state that abstraction supports mental travel, and that mental travel critically relies on abstraction. I propose an important addition to this theoretical framework, namely that mental travel might also support abstraction. Specifically, I argue that spontaneous mental travel (mind wandering), much like data augmentation in machine learning, provides variability in mental content and context necessary for abstraction.

Download Full-text

Deep neural networks trained with heavier data augmentation learn features closer to representations in hIT

10.32470/ccn.2018.1046-0 ◽

2018 ◽

Author(s):

Alex Hernández-García ◽

Johannes Mehrer ◽

Nikolaus Kriegeskorte ◽

Peter König ◽

Tim C. Kietzmann

Keyword(s):

Neural Networks ◽

Deep Neural Networks ◽

Data Augmentation

Download Full-text

Comparison of Nonlinear Spatial Correlation Models by the Influence of the Data Augmentation to the Classification Risk

Nonlinear Analysis Modelling and Control ◽

10.15388/na.2002.7.1.15200 ◽

2002 ◽

Vol 7 (1) ◽

pp. 31-42

Author(s):

J. Šaltytė ◽

K. Dučinskas

Keyword(s):

Spatial Correlation ◽

Random Fields ◽

Data Augmentation ◽

Gaussian Random Fields ◽

Classification Rule ◽

Numerical Comparison ◽

First Order ◽

Bayesian Risk ◽

Correlation Models

The Bayesian classification rule used for the classification of the observations of the (second-order) stationary Gaussian random fields with different means and common factorised covariance matrices is investigated. The influence of the observed data augmentation to the Bayesian risk is examined for three different nonlinear widely applicable spatial correlation models. The explicit expression of the Bayesian risk for the classification of augmented data is derived. Numerical comparison of these models by the variability of Bayesian risk in case of the first-order neighbourhood scheme is performed.

Download Full-text