English
Related papers

Related papers: Diet deep generative audio models with structured …

200 papers

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…

Machine Learning · Computer Science 2021-02-02 Siqiao Ruan , Ian Colbert , Ken Kreutz-Delgado , Srinjoy Das

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…

Machine Learning · Computer Science 2024-03-01 Advait Gadhikar , Rebekka Burkholz

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…

Computation and Language · Computer Science 2022-09-20 Yi Yang , Chen Zhang , Benyou Wang , Dawei Song

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…

Sound · Computer Science 2018-06-27 Rachel Manzelli , Vijay Thakkar , Ali Siahkamari , Brian Kulis

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…

Computer Vision and Pattern Recognition · Computer Science 2025-01-27 Md. Ismail Hossain , Mohammed Rakib , M. M. Lutfe Elahi , Nabeel Mohammed , Shafin Rahman

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…

Machine Learning · Computer Science 2025-12-30 Hamed Damirchi , Cristian Rodriguez-Opazo , Ehsan Abbasnejad , Zhen Zhang , Javen Shi

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…

Machine Learning · Computer Science 2017-05-08 Nicolas Keriven , Anthony Bourrier , Rémi Gribonval , Patrick Pérez

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…

Machine Learning · Computer Science 2018-09-06 Elchanan Mossel

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…

Machine Learning · Computer Science 2026-04-10 Zeran Johannsen

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…

Computer Vision and Pattern Recognition · Computer Science 2023-10-25 Maryam Hashemi , Ghazaleh Mahmoudi , Sara Kodeiri , Hadi Sheikhi , Sauleh Eetemadi

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,…

Sound · Computer Science 2025-11-26 Genís Plaja-Roglans , Yun-Ning Hung , Xavier Serra , Igor Pereira

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…

Sound · Computer Science 2019-02-18 Jordi Pons , Xavier Serra

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.…

Computation and Language · Computer Science 2017-09-07 Pranay Dighe , Gil Luyet , Afsaneh Asaei , Herve Bourlard

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…

Computer Vision and Pattern Recognition · Computer Science 2021-10-11 Srikumar Ramalingam , Daniel Glasner , Kaushal Patel , Raviteja Vemulapalli , Sadeep Jayasumana , Sanjiv Kumar

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…

Sound · Computer Science 2024-07-11 Marcella Astrid , Enjie Ghorbel , Djamila Aouada

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…

Cryptography and Security · Computer Science 2022-07-27 Tejumade Afonja , Lucas Bourtoule , Varun Chandrasekaran , Sageev Oore , Nicolas Papernot

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…

Computer Vision and Pattern Recognition · Computer Science 2020-11-23 Matthia Sabatelli , Mike Kestemont , Pierre Geurts

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…

Sound · Computer Science 2021-07-09 Prateek Verma , Chris Chafe