In deep learning research, many melody extraction models rely on redesig...
Diffusion models have shown promising results in cross-modal generation
...
Recent work has studied text-to-audio synthesis using large amounts of p...
In this paper, we develop machine learning techniques to identify unknow...
Membership Inference attacks (MIAs) aim to predict whether a data sample...
In this work we present an approach for generating alternative text (or
...
With the advent of fluent generative language models that can produce
co...
Universal source separation (USS) is a fundamental research task for
com...
The topic of Climate Change (CC) has received limited attention in NLP
d...
Contrastive learning has been successfully used for retrieval of semanti...
Recent years have seen progress beyond domain-specific sound separation ...
Contrastive learning has shown remarkable success in the field of multim...
User-generated social media data is constantly changing as new trends
in...
In this work we present a new approach for the task of predicting finger...
Choral music separation refers to the task of extracting tracks of voice...
Existing approaches for generating multitrack music with transformer mod...
Large language models are shown to present privacy risks through memoriz...
One of the most impressive results of recent NLP history is the ability ...
Recent work on controlled text generation has either required attribute-...
A limitation of current neural dialog models is that they tend to suffer...
The wide adoption and application of Masked language models (MLMs) on
se...
Music performance synthesis aims to synthesize a musical score into a na...
Singing melody extraction is an important problem in the field of music
...
Audio classification is an important task of mapping audio samples into ...
We show that a simple unsupervised masking objective can approach near
s...
We present a self-supervised pre-training approach for learning rich vis...
Physical measurements constitute a large portion of numbers in academic
...
Deep learning techniques for separating audio into different sound sourc...
Fine-tuning large pre-trained language models on downstream tasks has be...
In this paper, we explore the task of automatically generating natural
l...
Global models are trained to be as generalizable as possible, with user
...
We propose a deep generative model that performs typography analysis and...
Text style can reveal sensitive attributes of the author (e.g. race or a...
Non-parametric neural language models (NLMs) learn predictive distributi...
Previous work has shown that neural architectures are able to perform op...
Modern keyboards allow a musician to play multiple instruments at the sa...
Humans often refer to personal narratives, life experiences, and events ...
While recent work has shown that scores from models trained by the ubiqu...
We present a system that allows users to train their own state-of-the-ar...
We conduct an empirical evaluation of extrapolation performance when
con...
Neural language models are known to have a high capacity for memorizatio...
Past work on story generation has demonstrated the usefulness of conditi...
Existing persona-grounded dialog models often fail to capture simple
imp...
In this paper, we present MusPy, an open source Python library for symbo...
Drawing an analogy with automatic image completion systems, we propose M...
Prototype-driven text generation uses non-parametric models that first c...
Informal romanization is an idiosyncratic process used by humans in info...
We propose a deep and interpretable probabilistic generative model to an...
We present a deep generative model for unsupervised text style transfer ...
We perform statistical analysis of the phenomenon of neology, the proces...