论文信息 - A posterior union model for robust speech recognition

A posterior union model for robust speech recognition

The probabilistic union model is extended from a conditional-probability formulation to a posterior-probability formulation for speech recognition. The new formulation allows the order of the model to be optimised for every single frame, thereby enhancing the capability of the model for dealing with nonstationary noise corruption.

Jie Lin | Ji Ming

[1] Francis Jack Smith,et al. Union: A new approach for combining sub-band observations for noisy speech recognition , 2001, Speech Commun..

[2] P Jancovic,et al. A probabilistic union model with automatic order selection for noisy speech recognition. , 2001, The Journal of the Acoustical Society of America.

[3] Phil D. Green,et al. Robust automatic speech recognition with missing and unreliable acoustic data , 2001, Speech Commun..

[4] Francis Jack Smith,et al. Robust speech recognition using probabilistic union models , 2002, IEEE Trans. Speech Audio Process..