Related papers: Ecologically-Constrained Task Arithmetic for Multi…
Acoustic scene classification (ASC) and acoustic event detection (AED) are different but related tasks. Acoustic events can provide useful information for recognizing acoustic scenes. However, most of the datasets are provided without…
Automatic recognition of insect sound could help us understand changing biodiversity trends around the world -- but insect sounds are challenging to recognize even for deep learning. We present a new dataset comprised of 26399 audio files,…
We propose a novel method to model hierarchical metrical structures for both symbolic music and audio signals in a self-supervised manner with minimal domain knowledge. The model trains and inferences on beat-aligned music signals and…
We propose ADAPT, a meta-learning algorithm that \emph{learns} task sampling proportions under an explicit token budget for multi-task instruction tuning. Instead of fixing task weights by hand, \adapt{} maintains a continuous distribution…
Graph is a highly generic and diverse representation, suitable for almost any data processing problem. Spectral graph theory has been shown to provide powerful algorithms, backed by solid linear algebra theory. It thus can be extremely…
In the global challenge of understanding and characterizing biodiversity, short species-specific genomic sequences known as DNA barcodes play a critical role, enabling fine-grained comparisons among organisms within the same kingdom of…
The recent development of Audio-based Distributional Semantic Models (ADSMs) enables the computation of audio and lexical vector representations in a joint acoustic-semantic space. In this work, these joint representations are applied to…
Constructing new and more challenging tasksets is a fruitful methodology to analyse and understand few-shot classification methods. Unfortunately, existing approaches to building those tasksets are somewhat unsatisfactory: they either…
Machine learning algorithms, when trained on audio recordings from a limited set of devices, may not generalize well to samples recorded using other devices with different frequency responses. In this work, a relatively straightforward…
One of the hallmarks of human intelligence is the ability to compose learned knowledge into novel concepts which can be recognized without a single training example. In contrast, current state-of-the-art methods require hundreds of training…
Multi-genre speaker recognition is becoming increasingly popular due to its ability to better represent the complexities of real-world applications. However, a major challenge is the significant shift in the distribution of speaker vectors…
Breast ultrasound interpretation requires simultaneous lesion segmentation and tissue classification. However, conventional multi-task learning approaches suffer from task interference and rigid coordination strategies that fail to adapt to…
Two questions regarding practitioners' use of patent embeddings arise: (i) Does one fine-tuning recipe suffice for all downstream applications? (ii) Is fine-tuning on one patent landscape sufficient for downstream application on other…
Advances in deep learning have resulted in state-of-the-art performance for many audio classification tasks but, unlike humans, these systems traditionally require large amounts of data to make accurate predictions. Not every person or…
In this research endeavor, it was hypothesized that the sound produced by animals during their vocalizations can be used as identifiers of the animal breed or species even if they sound the same to unaided human ear. To test this…
Objective: This work proposes a semi-supervised training approach for detecting lung and heart sounds simultaneously with only one trained model and in invariance to the auscultation point. Methods: We use open-access data from the 2016…
Dialogue acts (DAs) can represent conversational actions of tutors or students that take place during tutoring dialogues. Automating the identification of DAs in tutoring dialogues is significant to the design of dialogue-based intelligent…
While insects are the largest and most diverse group of terrestrial animals, constituting ca. 80% of all known species, they are difficult to study due to their small size and similarity between species. Conventional monitoring techniques…
The rapid advancement of fake voice generation technology has ignited a race with detection systems, creating an urgent need to secure the audio ecosystem. However, existing benchmarks suffer from a critical limitation: they typically…
Few-shot learning is a type of classification through which predictions are made based on a limited number of samples for each class. This type of classification is sometimes referred to as a meta-learning problem, in which the model learns…