arXiv subjects

Clement Laroche

Publications and source records attributed to Clement Laroche.

3 recordsLinked to original sources

arXiv2024

Scalable Speech Enhancement with Dynamic Channel Pruning

Speech Enhancement (SE) is essential for improving productivity in remote collaborative environments. Although deep learning models are highly effective at SE, their computational demands make them impractical for embedded systems. Furthermore, acoustic conditions can change significantly in terms of difficulty, whereas neural networks are usually static with regard to the amount of computation performed. To this end, we introduce Dynamic Channel Pruning to the audio domain for the first time and apply it to a custom convolutional architecture for SE. Our approach works by identifying unnecessary convolutional channels at runtime and saving computational resources by not computing the activations for these channels and retrieving their filters. When trained to only use 25% of channels, we save 29.6% of MACs while only causing a 0.75% drop in PESQ. Thus, DynCP offers a promising path toward deploying larger and more powerful SE solutions on resource-constrained devices.

eess.AS↗

arXiv2020

Demystifying Orthogonal Monte Carlo and Beyond

Orthogonal Monte Carlo (OMC) is a very effective sampling algorithm imposing structural geometric conditions (orthogonality) on samples for variance reduction. Due to its simplicity and superior performance as compared to its Quasi Monte Carlo counterparts, OMC is used in a wide spectrum of challenging machine learning applications ranging from scalable kernel methods to predictive recurrent neural networks, generative models and reinforcement learning. However theoretical understanding of the method remains very limited. In this paper we shed new light on the theoretical principles behind OMC, applying theory of negatively dependent random variables to obtain several new concentration results. We also propose a novel extensions of the method leveraging number theory techniques and particle algorithms, called Near-Orthogonal Monte Carlo (NOMC). We show that NOMC is the first algorithm consistently outperforming OMC in applications ranging from kernel methods to approximating distances in probabilistic metric spaces.

cs.LG↗

arXiv2017

Matrix representations by means of interpolation

We examine implicit representations of parametric or point cloud models, based on interpolation matrices, which are not sensitive to base points. We show how interpolation matrices can be used for ray shooting of a parametric ray with a surface patch, including the case of high-multiplicity intersections. Most matrix operations are executed during pre-processing since they solely depend on the surface. For a given ray, the bottleneck is equation solving. Our Maple code handles bicubic patches in $\le 1$~sec, though numerical issues might arise. Our second contribution is to extend the method to parametric space curves and, generally, to codimension $> 1$, by computing the equations of (hyper)surfaces intersecting precisely at the given object. By means of Chow forms, we propose a new, practical, randomized algorithm that always produces correct output but possibly with a non-minimal number of surfaces. For space curves, we obtain 3 surfaces whose polynomials are of near-optimal degree; in this case, computation reduces to a Sylvester resultant. We illustrate our algorithm through a series of examples and compare our Maple prototype with other methods implemented in Maple i.e., Groebner basis and implicit matrix representations. Our Maple prototype is not faster but yields fewer equations and seems more robust than Maple's {\tt implicitize}; it is also comparable with the other methods for degrees up to 6.

math.AG↗