Faster Than Fast: Accelerating the Griffin-Lim Algorithm

Nenov, Rossen; Nguyen, Dang-Khoa; Balázs, Péter

doi:10.1109/icassp49357.2023.10097224

Cited by 4 publications

(1 citation statement)

References 28 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…These original data augmentation sets are augmented by MFS-CapsuleGAN, and CGAD (CapsuleGAN augmented data) is generated. To visually verify the authenticity of CGAD, the fast Griffin-Lim algorithm [24] is used to reconstruct the audio signal of randomly selected data when MFS-CapsuleGAN data is output. When each batch of data is augmented, the randomly generated audio signal sample data is output for the human ear and spectrum analysis verification.…”

Section: Mfs-capsulegan For Data Augmentationmentioning

confidence: 99%

Data Augmented of Mechanical Fault Sound Signal based on Generative Adversarial Networks

Yang,

Su,

2023

Period. Polytech. Elec. Eng. Comp. Sci.

View full text Add to dashboard Cite

In this paper, a global average pooling convolutional neural network based on CNN is proposed for mechanical fault sound detection, which called as GCMD. To solve the data scarcity of mechanical fault sound data, a spectrum frame selection augmented method based on log Mel spectrum feature is proposed to augment the original data, that aim is to train GCMD and generate counter networks. In order to solve the unbalance problem of data set and further improve the generalization ability of GCMD, an augmented neural network model based on CapsuleGAN was proposed, which called MFS-CapsuleGAN. The model was evaluated on the augmented data set by training GCMD neural network. Compared with the original data set, the accurate recognition rate of the model was improved by 23.7%. The performance of this method is improved significantly, which proves the feasibility and effectiveness of MFS-CapsuleGAN data augmented. In addition, the data set with background noise was used to test the generalization ability of GCMD network. The fluctuation range was within 0.117, indicating the good robustness of GCMD network.

show abstract

Section: Mfs-capsulegan For Data Augmentationmentioning

confidence: 99%

Data Augmented of Mechanical Fault Sound Signal based on Generative Adversarial Networks

Yang,

Su,

2023

Period. Polytech. Elec. Eng. Comp. Sci.

View full text Add to dashboard Cite

show abstract

Stable phase retrieval and perturbations of frames

Alharbi,

Freeman,

Ghoreishi

et al. 2023

Proc. Amer. Math. Soc. Ser. B

View full text Add to dashboard Cite

A frame ( x j ) j ∈ J (x_j)_{j\in J} for a Hilbert space H H is said to do phase retrieval if for all distinct vectors x , y ∈ H x,y\in H the magnitudes of the frame coefficients ( | ⟨ x , x j ⟩ | ) j ∈ J (|\langle x, x_j\rangle |)_{j\in J} and ( | ⟨ y , x j ⟩ | ) j ∈ J (|\langle y, x_j\rangle |)_{j\in J} distinguish x x from y y (up to a unimodular scalar). A frame which does phase retrieval is said to do C C -stable phase retrieval if the recovery of any vector x ∈ H x\in H from the magnitude of the frame coefficients is C C -Lipschitz. It is known that if a frame does stable phase retrieval then any sufficiently small perturbation of the frame vectors will do stable phase retrieval, though with a slightly worse stability constant. We provide new quantitative bounds on how the stability constant for phase retrieval is affected by a small perturbation of the frame vectors. These bounds are significant in that they are independent of the dimension of the Hilbert space and the number of vectors in the frame.

show abstract