Related papers: AVEX: What Matters for Animal Vocalization Encodin…

We propose a shift towards end-to-end learning in bird sound monitoring by combining self-supervised (SSL) and deep active learning (DAL). Leveraging transformer models, we aim to bypass traditional spectrogram conversions, enabling direct…

In the highly constrained context of low-resource language studies, we explore vector representations of speech from a pretrained model to determine their level of abstraction with regard to the audio signal. We propose a new unsupervised…

Acoustic data provide scientific and engineering insights in fields ranging from biology and communications to ocean and Earth science. We survey the recent advances and transformative potential of machine learning (ML), including deep…

We propose a semi-supervised singing synthesizer, which is able to learn new voices from audio data only, without any annotations such as phonetic segmentation. Our system is an encoder-decoder model with two encoders, linguistic and…

Automated audio captioning (AAC), a task that mimics human perception as well as innovatively links audio processing and natural language processing, has overseen much progress over the last few years. AAC requires recognizing contents such…

Can artificial intelligence unlock the secrets of the human brain? How do the inner mechanisms of deep learning models relate to our neural circuits? Is it possible to enhance AI by tapping into the power of brain recordings? These…

Language plays a critical role in Vision-Language-Action (VLA) models, yet the linguistic characteristics of the datasets used to train and evaluate these systems remain poorly documented. In this work, we present a systematic dataset audit…

Significant strides have been made in creating voice identity representations using speech data. However, the same level of progress has not been achieved for singing voices. To bridge this gap, we suggest a framework for training singer…

A main challenge in applying deep learning to music processing is the availability of training data. One potential solution is Multi-task Learning, in which the model also learns to solve related auxiliary tasks on additional datasets to…

Animal vocalizations contain sequential structures that carry important communicative information, yet most computational bioacoustics studies average the extracted frame-level features across the temporal axis, discarding the order of the…

The Encoder-Decoder architecture is a main stream deep learning model for biomedical image segmentation. The encoder fully compresses the input and generates encoded features, and the decoder then produces dense predictions using encoded…

Sound recordings are used in various ecological studies, including acoustic wildlife monitoring. Such surveys require automatic detection of target sound events. However, current detectors, especially those relying on band-limited energy,…

Audio classification can distinguish different kinds of sounds, which is helpful for intelligent applications in daily life. However, it remains a challenging task since the sound events in an audio clip is probably multiple, even…

Taking advantage of the structure of large datasets to pre-train Deep Learning models is a promising strategy to decrease the need for supervised data. Self-supervised learning methods, such as contrastive and its variation are a promising…

This paper proposes a data-efficient, semi-supervised, two-pass framework for segmenting bird vocalizations. The framework utilizes a binary classification model to categorize frames of an input audio recording into the background or bird…

The imitation of percussive instruments via the human voice is a natural way for us to communicate rhythmic ideas and, for this reason, it attracts the interest of music makers. Specifically, the automatic mapping of these vocal imitations…

The objective of deep learning methods based on encoder-decoder architectures for music source separation is to approximate either ideal time-frequency masks or spectral representations of the target music source(s). The spectral…

Since the vocal component plays a crucial role in popular music, singing voice detection has been an active research topic in music information retrieval. Although several proposed algorithms have shown high performances, we argue that…

Deep speaker embeddings have shown promising results in speaker recognition, as well as in other speaker-related tasks. However, some issues are still under explored, for instance, the information encoded in these representations and their…

Artificial neural networks are increasingly powerful models of brain computation, yet it remains unclear whether improving their performance in downstream tasks also makes their internal representations more similar to brain signals. To…