# Non-negative subspace projection during conventional MFCC feature extraction for noise robust speech recognition

##### Citations

2 citations

### Cites methods from "Non-negative subspace projection du..."

...In an other work, orthogonal projection technique is used to remove the stress component from stressed speech [6–9]....

[...]

##### References

11,500 citations

### "Non-negative subspace projection du..." refers background in this paper

...gives the following iterative update rules [4], [5] for refining the matrices Wand H: Ln hrnvmn/[WH]mn Wmr := Wmr '\' h L....

[...]

9,604 citations

7,345 citations

### "Non-negative subspace projection du..." refers background in this paper

...gives the following iterative update rules [4], [5] for refining the matrices Wand H: Ln hrnvmn/[WH]mn Wmr := Wmr '\' h L....

[...]

388 citations

### "Non-negative subspace projection du..." refers methods in this paper

...In [3], log-Mel filterbank features of noisy speech were represented using exemplars (dictionary) of speech and noise bases....

[...]

384 citations

### "Non-negative subspace projection du..." refers background or methods in this paper

...The HLDA transformation matrix is estimated in maximum likelihood (ML) framework after building the acoustic models using 39 dimensional MFCCs as described in [7], and is applied to both feature vectors and the models in the conventional method....

[...]

...When the classes have diagonal covariances, if the feature vectors are correlated within a class, HLDA reduces the correlation [7] and increases the likelihood of the model, thus improving the recognition accuracy....

[...]