Related papers: On the Futility of Learning Complex Frame-Level La…

Neural networks are very powerful learning systems, but they do not readily generalize from one task to the other. This is partly due to the fact that they do not learn in a compositional way, that is, by discovering skills that are shared…

Robust language processing systems are becoming increasingly important given the recent awareness of dangerous situations where brittle machine learning models can be easily broken with the presence of noises. In this paper, we introduce a…

Countless learning tasks require dealing with sequential data. Image captioning, speech synthesis, and music generation all require that a model produce outputs that are sequences. In other domains, such as time series prediction, video…

We present a new approach to evaluate chord recognition systems on songs which do not have full annotations. The principle is to use online chord databases to generate high accurate "pseudo annotations" for these songs and compute "pseudo…

Audio processors whose parameters are modified periodically over time are often referred as time-varying or modulation based audio effects. Most existing methods for modeling these type of effect units are often optimized to a very specific…

Large audio language models are increasingly used for complex audio understanding tasks, but they struggle with temporal tasks that require precise temporal grounding, such as word alignment and speaker diarization. The standard approach,…

Neural dynamical systems with stable attractor structures, such as point attractors and continuous attractors, are hypothesized to underlie meaningful temporal behavior that requires working memory. However, working memory may not support…

It has been observed that neural networks perform poorly when the data or tasks are presented sequentially. Unlike humans, neural networks suffer greatly from catastrophic forgetting, making it impossible to perform life-long learning. To…

Multi-modal contrastive learning techniques in the audio-text domain have quickly become a highly active area of research. Most works are evaluated with standard audio retrieval and classification benchmarks assuming that (i) these models…

Discriminative segmental models offer a way to incorporate flexible feature functions into speech recognition. However, their appeal has been limited by their computational requirements, due to the large number of possible segments to…

Sequence prediction and classification are ubiquitous and challenging problems in machine learning that can require identifying complex dependencies between temporally distant inputs. Recurrent Neural Networks (RNNs) have the ability, in…

Restricted Boltzmann Machines (RBMs) are generative models which can learn useful representations from samples of a dataset in an unsupervised fashion. They have been widely employed as an unsupervised pre-training method in machine…

The early detection of potential failures in industrial machinery components is paramount for ensuring the reliability and safety of operations, thereby preserving Machine Condition Monitoring (MCM). This research addresses this imperative…

Machine hearing or listening represents an emerging area. Conventional approaches rely on the design of handcrafted features specialized to a specific audio task and that can hardly generalized to other audio fields. For example,…

One of the challenges of the Optical Music Recognition task is to transcript the symbols of the camera-captured images into digital music notations. Previous end-to-end model which was developed as a Convolutional Recurrent Neural Network…

We introduce a new neural architecture and an unsupervised algorithm for learning invariant representations from temporal sequence of images. The system uses two groups of complex cells whose outputs are combined multiplicatively: one that…

The fine-tuning of deep pre-trained models has revealed compositional properties, with multiple specialized modules that can be arbitrarily composed into a single, multi-task model. However, identifying the conditions that promote…

In this paper, we provide a deep analysis of temporal modeling for action recognition, an important but underexplored problem in the literature. We first propose a new approach to quantify the temporal relationships between frames captured…

Several recent polyphonic music transcription systems have utilized deep neural networks to achieve state of the art results on various benchmark datasets, pushing the envelope on framewise and note-level performance measures. Unfortunately…

Large language models (LLMs) are typically trained on shuffled corpora, yielding models whose knowledge is frozen at train time and whose temporal grounding remains poorly understood. In this work, we study the impact of pre-training…