Audio-visual codebook dependent cepstral normalization
View Patent ↗An arrangement for yielding enhanced audio features towards the provision of enhanced audio-visual features for speech recognition. Input is provided in the form of noisy audio-visual features and noisy audio features related to the noisy audio-visual features.
1. A system for enhancing speech for speech recognition, said system comprising:
a processor;
a memory storing code accessible by the processor to
obtain noisy audio-visual features;
obtain noisy audio features related to the noisy audio-visual features; and
use a cepstral speech function operating on the noisy audio features and the noisy audio-visual features to yield enhanced audio features that are re-combined with visual features to yield enhanced audio-visual features for speech recognition.
2. The system according to claim 1 , wherein yielding enhanced audio features comprises yielding estimated clean speech features.
3. The system according to claim 1 , wherein yielding enhanced audio features comprises determining a posterior distribution based on the noisy audio-visual features.
4. The system according to claim 3 , wherein said determining a posterior distribution comprises determining a posterior distribution based additionally on Gaussian parameters which model a probability density function related to the noisy audio-visual features.
5. The system according to claim 1 , wherein said yielding enhanced audio features comprises estimating audio compensation codewords.
6. The system according to claim 1 , wherein yielding enhanced audio features comprises determining the differences between the noisy audio features and modified noisy audio-visual features.
7. The system according to claim 1 , wherein yielding enhanced audio features comprises:
determining a posterior distribution based on the noisy audio-visual features; and
estimating audio compensation codewords.
8. The system according to claim 7 , wherein yielding enhanced audio features comprises effecting a multiplication of the posterior distribution with the estimated audio compensation codewords.
9. The system according to claim 8 , wherein said yielding enhanced audio features comprises determining the difference between the noisy audio features and the multiplication of the posterior distribution with the estimated audio compensation codewords.
10. The system according to claim 1 , wherein said obtaining noisy audio-visual features comprises obtaining noisy audio-visual features which have resulted from the processing of normalized audio features and normalized video features.