Dynamic compensation of HMM variances using the feature enhancement uncertainty computed from a parametric model of speech distortion

By Li Deng, Jasha Droppo, A. Acero. 2005

181 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Signal Processing

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Shinji Watanabe
2. Jinyu Li
3. Dong Yu
4. Deliang Wang
5. John R. Hershey
6. Arun Narayanan
7. Yoshua Bengio
8. Li Deng

In Signal Processing

1. Deliang Wang
2. Dong Yu
3. Shinji Watanabe
4. John R. Hershey
5. Jinyu Li
6. Li Deng
7. Arun Narayanan
8. Jonathan Le Roux

Citations in the corpus

• Deep Learning: Methods and Applications (2014, methodology): “However, the same paper also shows that a model of [278] in which a sophisticated signal processing technique for extracting visual features, together with the uncertainty-compensation method developed originally from robust speech recognition [104], gives the best classification accuracy in the cro”
• A tutorial survey of architectures, algorithms, and applications for deep learning (2014, methodology): “However, the same paper also shows that a model of [194] in which a sophisticated signal processing technique for extracting visual features, together with the uncertainty-compensation method developed originally from robust speech recognition [195], gives the best classification accuracy in the cro”
• Adaptive Multimodal Fusion by Uncertainty Compensation With Application to Audiovisual Speech Recognition (2009, methodology): “After canceling out shape deformation, the face texture registered with the mean face can be modeled as a weighted sum of “eigentextures” , i.e., (22) where is the mean face texture.”
• Investigation of Speech Separation as a Front-End for Noise Robust Speech Recognition (2014, background): “The best performances are usually obtained by combining feature-based and model-based approaches (e.g., an uncertainty decoding framework [8]).”
• Hierarchical learning : theory with applications in speech and vision (2009, background): “A large fraction of the noise-robust speech recognition literature has traditionally centered on either front-end post-processing of standard features [73, 22, 32] or modifying recognizer model parameters to compensate for train/test noise mismatch [33], rather than the design of inherently noise-ro”
• Uncertainty propagation through deep neural networks (2015, methodology): “In [8], the acoustic scores have been modified to match the observation uncertainties in a similar way as used in the uncertainty decoding approach [4], which has first been introduced for GMM-based ASR systems.”