Related papers: Learnable Frontends that do not Learn: Quantifying…

Accurately interpreting cardiac auscultation signals plays a crucial role in diagnosing and managing cardiovascular diseases. However, the paucity of labelled data inhibits classification models' training. Researchers have turned to…

Insect population numbers and biodiversity have been rapidly declining with time, and monitoring these trends has become increasingly important for conservation measures to be effectively implemented. But monitoring methods are often…

Monitoring of bird populations has played a vital role in conservation efforts and in understanding biodiversity loss. The automation of this process has been facilitated by both sensing technologies, such as passive acoustic monitoring,…

Recurrent Neural Networks (RNNs) can be seriously impacted by the initial parameters assignment, which may result in poor generalization performances on new unseen data. With the objective to tackle this crucial issue, in the context of RNN…

In speech deepfake detection, one of the critical aspects is developing detectors able to generalize on unseen data and distinguish fake signals across different datasets. Common approaches to this challenge involve incorporating diverse…

In recent years, speaker recognition systems based on raw waveform inputs have received increasing attention. However, the performance of such systems are typically inferior to the state-of-the-art handcrafted feature-based counterparts,…

Tool learning has emerged as a promising direction by extending Large Language Models' (LLMs) capabilities with external tools. Existing tool learning studies primarily focus on the general-purpose tool-use capability, which addresses…

Privacy preservation has long been a concern in smart acoustic monitoring systems, where speech can be passively recorded along with a target signal in the system's operating environment. In this study, we propose the integration of two…

Aligning language models (LMs) with preferences is an important problem in natural language generation. A key challenge is that preferences are typically provided at the sequence level while LM training and generation both occur at the…

Sound sources localization using multichannel signal processing has been a subject of active research for decades. In recent years, the use of deep learning in audio signal processing has allowed to drastically improve performances for…

Deep neural networks are inherently opaque and challenging to interpret. Unlike hand-crafted feature-based models, we struggle to comprehend the concepts learned and how they interact within these models. This understanding is crucial not…

Personalization of the amplification function of hearing aids has been shown to be of benefit to hearing aid users in previous studies. Several machine learning-based personalization approaches have been introduced in the literature. This…

Self-supervised learning enables the training of large neural models without the need for large, labeled datasets. It has been generating breakthroughs in several fields, including computer vision, natural language processing, biology, and…

This work introduces a wavelet neural network to learn a filter-bank specialized to fit non-stationary signals and improve interpretability and performance for digital signal processing. The network uses a wavelet transform as the first…

Passive acoustic monitoring (PAM) in avian bioacoustics enables cost-effective and extensive data collection with minimal disruption to natural habitats. Despite advancements in computational avian bioacoustics, deep learning models…

Large language models (LLMs) remain vulnerable to misalignment and jailbreaks, making external safeguards like moderation filters essential, yet existing filters often focus narrowly on safety, falling short of the broader alignment needs…

Information on speaker characteristics can be useful as side information in improving speaker recognition accuracy. However, such information is often private. This paper investigates how privacy-preserving learning can improve a speaker…

Speech separation aims to separate multiple speech sources from a speech mixture. Although speech separation is well-solved on some existing English speech separation benchmarks, it is worthy of more investigation on the generalizability of…

Network pruning is a promising avenue for compressing deep neural networks. A typical approach to pruning starts by training a model and then removing redundant parameters while minimizing the impact on what is learned. Alternatively, a…

Phoneme-level computer-assisted pronunciation training systems typically rely on phoneme-level annotations, which are costly and scarce. In this work, we investigate whether phoneme-level mispronunciation information can be learned without…