On the Versatile Uses of Partial Distance Correlation in Deep Learning

Zhen, Xingjian; Meng, Zihang; Chakraborty, Rudrasis; Singh, Vikas

doi:10.1007/978-3-031-19809-0_19

Cited by 9 publications

(2 citation statements)

References 28 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It has good applicability to the relationship between variables, whether linear or nonlinear and is not limited by other parameters or models [15] , overcoming the disadvantage that Pearson's correlation coefficient can only measure the degree of linear correlation. At present, the distance correlation coefficient has achieved considerable success in several fields including image recognition [16] .…”

Section: Audio Matching Using Distance Correlation Coefficientsmentioning

confidence: 99%

An Improved Philips Algorithm

2024

AJCIS

View full text Add to dashboard Cite

As a classical audio fingerprint algorithm, the Philips algorithm has been widely used. However, the feature extraction module of the Philips algorithm is inefficient and time-consuming, and the feature binarization algorithm is susceptible to noise interference, which affects the correct rate of audio fingerprint matching. To solve the problems mentioned, this paper proposes an improved Philips audio fingerprint algorithm. The Gammatone filter bank is used to analyze the frequency spectrum of the audio signal to simulate the frequency-selective characteristic of the basilar membrane of the human ear, and a graph-convolutional neural network is introduced to extract the global features between different frequency bands. The distance correlation coefficient is used to calculate the distance between the audio feature matrices to achieve the matching of audio fingerprints. The experimental results show that compared with the original Philips algorithm, the algorithm proposed in this paper achieves lower time consumption and stronger noise immunity.

show abstract

Section: Audio Matching Using Distance Correlation Coefficientsmentioning

confidence: 99%

An Improved Philips Algorithm

2024

AJCIS

View full text Add to dashboard Cite

show abstract

“…DC [32,33] provides a statistical measure of dependence between random vectors. Consider the hidden representation Hi ∈ R B×D i , where the row vector h i k ∈ R D i corresponds to the i-th layer's response of the k-th sample.…”

Section: DCmentioning

confidence: 99%

CoMFLP: Correlation Measure Based Fast Search on ASR Layer Pruning

Liu¹,

Peng²,

Lee³

2023

Interspeech 2023

View full text Add to dashboard Cite

Transformer-based speech recognition (ASR) model with deep layers exhibited significant performance improvement. However, the model is inefficient for deployment on resourceconstrained devices. Layer pruning (LP) is a commonly used compression method to remove redundant layers. Previous studies on LP usually identify the redundant layers according to a task-specific evaluation metric. They are time-consuming for models with a large number of layers, even in a greedy search manner. To address this problem, we propose CoM-FLP, a fast search LP algorithm based on correlation measure. The correlation between layers is computed to generate a correlation matrix, which identifies the redundancy among layers. The search process is carried out in two steps: (1) coarse search: to determine top K candidates by pruning the most redundant layers based on the correlation matrix; (2) fine search: to select the best pruning proposal among K candidates using a task-specific evaluation metric. Experiments on an ASR task show that the pruning proposal determined by CoMFLP outperforms existing LP methods while only requiring constant time complexity. The code is publicly available at https://github.com/louislau1129/CoMFLP.

show abstract