Unsupervised learning of phonemes of whispered speech in a noisy environment based on convolutive non-negative matrix factorization

DOI10.1016/J.INS.2013.09.037MaRDI QIDQ498019zbMATH OpenOpenAlexFDO

Authors Yong-Cai Geng, Sumit K. Garg

Publication date 25 September 2015

Published in Information Sciences (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1016/j.ins.2013.09.037

zbMATH Keywords

non-negative matrix factorizationunsupervised phoneme base learningwhisper intelligibility enhancement

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05) Pattern recognition, speech recognition (68T10) Measures of information, entropy (94A17)

Recommendations

• Discovering Convolutive Speech Phones Using Sparseness and Non-negativity
• Improving speech enhancement in unseen noise using deep convolutional neural network

Cites work

• Learning the parts of objects by non-negative matrix factorization
• Multi-adjoint property-oriented and object-oriented concept lattices
• Rough set model based on formal concept analysis
• Speech enhancement for non-stationary noise environments
• The auditory organization of speech and other sources in listeners and computational models

Cited in

(5)

• Investigation of the Lombard effect based on a machine learning approach
• Lagrange stability of neural networks with memristive synapses and multiple delays
• Robust Manhattan non-negative matrix factorization for image recovery and representation
• Unvoiced speech recognition using tissue-conductive acoustic sensor
• Projective robust nonnegative factorization

This page was built for publication: Unsupervised learning of phonemes of whispered speech in a noisy environment based on convolutive non-negative matrix factorization

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q498019)