Related papers: Diet deep generative audio models with structured …
The use of Deep Learning hardware algorithms for embedded applications is characterized by challenges such as constraints on device power consumption, availability of labeled data, and limited internet bandwidth for frequent training on…
Learning Rate Rewinding (LRR) has been established as a strong variant of Iterative Magnitude Pruning (IMP) to find lottery tickets in deep overparameterized neural networks. While both iterative pruning schemes couple structure and…
Over-parameterized models, typically pretrained language models (LMs), have shown an appealing expressive power due to their small learning bias. However, the huge learning capacity of LMs can also lead to large learning variance. In a…
Existing automatic music generation approaches that feature deep learning can be broadly classified into two types: raw audio models and symbolic models. Symbolic models, which train and generate at the note level, are currently the more…
Pruning refers to the elimination of trivial weights from neural networks. The sub-networks within an overparameterized model produced after pruning are often called Lottery tickets. This research aims to generate winning lottery tickets…
The Lottery Ticket Hypothesis (LTH) suggests that over-parameterized neural networks contain sparse subnetworks ("winning tickets") capable of matching full model performance when trained from scratch. With the growing reliance on…
Likelihood-based deep generative models have recently been shown to exhibit pathological behaviour under the manifold hypothesis as a consequence of using high-dimensional densities to model data with low-dimensional structure. In this…
Learning parameters from voluminous data can be prohibitive in terms of memory and computational requirements. We propose a "compressive learning" framework where we estimate model parameters from a sketch of the training data. This sketch…
It is argued that deep learning is efficient for data that is generated from hierarchal generative models. Examples of such generative models include wavelet scattering networks, functions of compositional structure, and deep rendering…
Classical statistical learning theory predicts that overparameterized models should exhibit severe overfitting, yet modern deep neural networks with far more parameters than training samples consistently generalize well. This contradiction…
Large-scale pretrained models such as LXMERT are becoming popular for learning cross-modal representations on text-image pairs for vision-language tasks. According to the lottery ticket hypothesis, NLP and computer vision models contain…
Extracting individual elements from music mixtures is a valuable tool for music production and practice. While neural networks optimized to mask or transform mixture spectrograms into the individual source(s) have been the leading approach,…
The computer vision literature shows that randomly weighted neural networks perform reasonably as feature extractors. Following this idea, we study how non-trained (randomly weighted) convolutional neural networks perform as feature…
We propose to model the acoustic space of deep neural network (DNN) class-conditional posterior probabilities as a union of low-dimensional subspaces. To that end, the training posteriors are used for dictionary learning and sparse coding.…
Deep generative models can generate high-fidelity audio conditioned on various types of representations (e.g., mel-spectrograms, Mel-frequency Cepstral Coefficients (MFCC)). Recently, such models have been used to synthesize audio waveforms…
Deep learning has yielded extraordinary results in vision and natural language processing, but this achievement comes at a cost. Most models require enormous resources during training, both in terms of computation and in human labeling…
The availability of highly convincing audio deepfake generators highlights the need for designing robust audio deepfake detectors. Existing works often rely solely on real and fake data available in the training set, which may lead to…
It is perhaps no longer surprising that machine learning models, especially deep neural networks, are particularly vulnerable to attacks. One such vulnerability that has been well studied is model extraction: a phenomenon in which the…
We study the generalization properties of pruned neural networks that are the winners of the lottery ticket hypothesis on datasets of natural images. We analyse their potential under conditions in which training data is scarce and comes…
This paper proposes a novel way of doing audio synthesis at the waveform level using Transformer architectures. We propose a deep neural network for generating waveforms, similar to wavenet. This is fully probabilistic, auto-regressive, and…