Related papers: PACE: Pretrained Audio Continual Learning
Biomedical audio signals, such as phonocardiograms (PCG), are inherently rhythmic and contain diagnostic information in both their spectral (tonal) and temporal domains. Standard 2D spectrograms provide rich spectral features but compromise…
Speech Emotion Recognition (SER) systems often assume congruence between vocal emotion and lexical semantics. However, in real-world interactions, acoustic-semantic conflict is common yet overlooked, where the emotion conveyed by tone…
Progress in speech processing has been facilitated by shared datasets and benchmarks. Historically these have focused on automatic speech recognition (ASR), speaker identification, or other lower-level tasks. Interest has been growing in…
Limited diversity in standardized benchmarks for evaluating audio representation learning (ARL) methods may hinder systematic comparison of current methods' capabilities. We present ARCH, a comprehensive benchmark for evaluating ARL methods…
Personalized speech enhancement (PSE) models achieve promising results compared with unconditional speech enhancement models due to their ability to remove interfering speech in addition to background noise. Unlike unconditional speech…
Continual learning methods based on pre-trained models (PTM) have recently gained attention which adapt to successive downstream tasks without catastrophic forgetting. These methods typically refrain from updating the pre-trained parameters…
Current communication technologies face limitations in terms of theoretical capacity, spectrum availability, and power resources. Pragmatic communication, leveraging terminal intelligence for selective data transmission, offers resource…
Parameter-efficient fine-tuning (PEFT) has enabled the efficient optimization of cumbersome language models in real-world settings. However, as datasets in such environments often contain noisy labels that adversely affect performance, PEFT…
Recent studies show that pretrained vision models can boost performance in audio downstream tasks. To enhance the performance further, an additional pretraining stage with large scale audio data is typically required to infuse audio…
Audio-Language Models (ALMs), trained on paired audio-text data, are designed to process, understand, and reason about audio-centric multimodal content. Unlike traditional supervised approaches that use predefined labels, ALMs leverage…
Fixed representational capacity is a fundamental constraint in continual learning: practitioners must guess an appropriate model width before training, without knowing how many distinct concepts the data contains. We propose LACE…
The full potential of large pretrained models remains largely untapped in control domains like robotics. This is mainly because of the scarcity of data and the computational challenges associated with training or fine-tuning these large…
Parameter-efficient fine-tuning for continual learning (PEFT-CL) has shown promise in adapting pre-trained models to sequential tasks while mitigating catastrophic forgetting problem. However, understanding the mechanisms that dictate…
Rapid development of large-scale pre-training has resulted in foundation models that can act as effective feature extractors on a variety of downstream tasks and domains. Motivated by this, we study the efficacy of pre-trained vision models…
Dementia, a progressive neurodegenerative disorder, affects memory, reasoning, and daily functioning, creating challenges for individuals and healthcare systems. Early detection is crucial for timely interventions that may slow disease…
Although text-to-speech (TTS) systems have significantly improved, most TTS systems still have limitations in synthesizing speech with appropriate phrasing. For natural speech synthesis, it is important to synthesize the speech with a…
Class-incremental learning (CIL) aims to enable models to continuously learn new classes while overcoming catastrophic forgetting. The introduction of pre-trained models has brought new tuning paradigms to CIL. In this paper, we revisit…
Self-supervised speech models learn representations that capture both content and speaker information. Yet this entanglement creates problems: content tasks suffer from speaker bias, and privacy concerns arise when speaker identity leaks…
This paper presents a novel approach to target speaker extraction (TSE) using Curriculum Learning (CL) techniques, addressing the challenge of distinguishing a target speaker's voice from a mixture containing interfering speakers. For…
Continual learning (CL) is crucial for evaluating adaptability in learning solutions to retain knowledge. Our research addresses the challenge of catastrophic forgetting, where models lose proficiency in previously learned tasks as they…