Adaptive speech model for missing-feature reconstruction

2016 IEEE International Conference on Digital Signal Processing (DSP) ◽

10.1109/icdsp.2016.7868525 ◽

2016 ◽

Author(s):

Hesdras O. Viana ◽

Aluizio F. R. Araujo

Keyword(s):

Speech Model ◽

Missing Feature ◽

Feature Reconstruction

Download Full-text

Band-Independent Mask Estimation for Missing-Feature Reconstruction in the Presence of Unknown Background Noise

2006 IEEE International Conference on Acoustics Speed and Signal Processing Proceedings ◽

10.1109/icassp.2006.1660018 ◽

2006 ◽

Author(s):

Wooil Kim ◽

R.M. Stern

Keyword(s):

Background Noise ◽

Mask Estimation ◽

Missing Feature ◽

Feature Reconstruction

Download Full-text

Vector Autoregressive Model for Missing Feature Reconstruction

Chinese Spoken Language Processing - Lecture Notes in Computer Science ◽

10.1007/11939993_35 ◽

2006 ◽

pp. 315-324

Author(s):

Xiong Xiao ◽

Haizhou Li ◽

Eng Siong Chng

Keyword(s):

Autoregressive Model ◽

Vector Autoregressive Model ◽

Vector Autoregressive ◽

Missing Feature ◽

Feature Reconstruction

Download Full-text

Missing-Feature Reconstruction by Leveraging Temporal Spectral Correlation for Robust Speech Recognition in Background Noise Conditions

IEEE Transactions on Audio Speech and Language Processing ◽

10.1109/tasl.2010.2041698 ◽

2010 ◽

Vol 18 (8) ◽

pp. 2111-2120 ◽

Author(s):

Wooil Kim ◽

J Hansen

Keyword(s):

Speech Recognition ◽

Background Noise ◽

Robust Speech Recognition ◽

Spectral Correlation ◽

Missing Feature ◽

Feature Reconstruction

Download Full-text

Time–Frequency Correlation-Based Missing-Feature Reconstruction for Robust Speech Recognition in Band-Restricted Conditions

IEEE Transactions on Audio Speech and Language Processing ◽

10.1109/tasl.2009.2015080 ◽

2009 ◽

Vol 17 (7) ◽

pp. 1292-1304 ◽

Author(s):

Wooil Kim ◽

J.H.L. Hansen

Keyword(s):

Speech Recognition ◽

Robust Speech Recognition ◽

Frequency Correlation ◽

Time Frequency ◽

Missing Feature ◽

Feature Reconstruction

Download Full-text

MMSE-Based Missing-Feature Reconstruction With Temporal Modeling for Robust Speech Recognition

IEEE Transactions on Audio Speech and Language Processing ◽

10.1109/tasl.2012.2229982 ◽

2013 ◽

Vol 21 (3) ◽

pp. 624-635 ◽

Author(s):

J. A. Gonzalez ◽

A. M. Peinado ◽

Ning Ma ◽

A. M. Gomez ◽

J. Barker

Keyword(s):

Speech Recognition ◽

Robust Speech Recognition ◽

Temporal Modeling ◽

Missing Feature ◽

Feature Reconstruction

Download Full-text

Missing-feature reconstruction for band-limited speech recognition in spoken document retrieval

10.21437/interspeech.2006-93 ◽

2006 ◽

Author(s):

Wooil Kim ◽

John H. L. Hansen

Keyword(s):

Speech Recognition ◽

Document Retrieval ◽

Spoken Document Retrieval ◽

Band Limited ◽

Missing Feature ◽

Feature Reconstruction

Download Full-text

Parameter Tuning-Free Missing-Feature Reconstruction for Robust Sound Recognition

IEEE Journal of Selected Topics in Signal Processing ◽

10.1109/jstsp.2020.3038054 ◽

2020 ◽

pp. 1-1

Author(s):

Qi Liu ◽

Jibin Wu

Keyword(s):

Parameter Tuning ◽

Sound Recognition ◽

Missing Feature ◽

Feature Reconstruction

Download Full-text

Missing Feature reconstruction with Multivariate Laplace distribution (MLD) for noise robust phoneme recognition

2008 3rd International Symposium on Communications, Control and Signal Processing ◽

10.1109/isccsp.2008.4537339 ◽

2008 ◽

Author(s):

Arash Mohammadi ◽

Farshad Almasganj ◽

Aboozar Taherkhani ◽

Farnoosh Naderkhani

Keyword(s):

Laplace Distribution ◽

Phoneme Recognition ◽

Noise Robust ◽

Multivariate Laplace Distribution ◽

Missing Feature ◽

Feature Reconstruction

Download Full-text

Missing-Feature Reconstruction With a Bounded Nonlinear State-Space Model

IEEE Signal Processing Letters ◽

10.1109/lsp.2011.2163508 ◽

2011 ◽

Vol 18 (10) ◽

pp. 563-566 ◽

Author(s):

Ulpu Remes ◽

Kalle J. Palomaki ◽

Tapani Raiko ◽

Antti Honkela ◽

Mikko Kurimo

Keyword(s):

State Space ◽

State Space Model ◽

Space Model ◽

Missing Feature ◽

Nonlinear State ◽

Feature Reconstruction

Download Full-text

Time-frequency correlation based missing-feature reconstruction for robust speech recognition in background noise conditions

2009 Conference Record of the Forty-Third Asilomar Conference on Signals, Systems and Computers ◽

10.1109/acssc.2009.5470200 ◽

2009 ◽

Author(s):

Wooil Kim ◽

John H.L. Hansen

Keyword(s):

Speech Recognition ◽

Background Noise ◽

Robust Speech Recognition ◽

Frequency Correlation ◽

Time Frequency ◽

Missing Feature ◽

Feature Reconstruction

Download Full-text