Related papers: AFT: An Exemplar-Free Class Incremental Learning M…

Continual learning (CL) aims to extend deep models from static and enclosed environments to dynamic and complex scenarios, enabling systems to continuously acquire new knowledge of novel categories without forgetting previously learned…

Currently used semantic parsing systems deployed in voice assistants can require weeks to train. Datasets for these models often receive small and frequent updates, data patches. Each patch requires training a new model. To reduce training…

Exemplar replay has become an effective strategy for mitigating catastrophic forgetting in federated continual learning (FCL) by retaining representative samples from past tasks. Existing studies focus on designing sample-importance…

Acoustic events are sounds with well-defined spectro-temporal characteristics which can be associated with the physical objects generating them. Acoustic scenes are collections of such acoustic events in no specific temporal order. Given…

Automatic Music Transcription (AMT) is a vital technology in the field of music information processing. Despite recent enhancements in performance due to machine learning techniques, current methods typically attain high accuracy in domains…

Fine-tuning large language models (LLMs) often causes overfitting to specific prompt wording, where minor phrasing variations drastically reduce performance. To address this, we propose Prompt-Agnostic Fine-Tuning (PAFT), a method that…

The rapid proliferation of wireless devices makes robust identity authentication essential. Radio Frequency Fingerprinting (RFF) exploits device-specific, hard-to-forge physical-layer impairments for identification, and is promising for IoT…

Recent advances in audio large language models (ALLMs) have made high-quality synthetic audio widely accessible, increasing the risk of malicious audio deepfakes across speech, environmental sounds, singing voice, and music. Real-world…

Foundation Models (FMs) have become the hallmark of modern AI, however, these models are trained on massive data, leading to financially expensive training. Updating FMs as new data becomes available is important, however, can lead to…

Acoustic Echo Cancellation (AEC) plays a key role in speech interaction by suppressing the echo received at microphone introduced by acoustic reverberations from loudspeakers. Since the performance of linear adaptive filter (AF) would…

The hindering problem in facial expression recognition (FER) is the presence of inaccurate annotations referred to as noisy annotations in the datasets. These noisy annotations are present in the datasets inherently because the labeling is…

Cross-entropy (CE) training provides dense and scalable supervision for language models, but it optimizes next-token prediction under teacher forcing rather than sequence-level behavior under model rollouts. We introduce a feature-matching…

Environmental Sound Classification (ESC) is an active research area in the audio domain and has seen a lot of progress in the past years. However, many of the existing approaches achieve high accuracy by relying on domain-specific features…

Handling distribution shifts from training data, known as out-of-distribution (OOD) generalization, poses a significant challenge in the field of machine learning. While a pre-trained vision-language model like CLIP has demonstrated…

Speech Foundation Models encounter significant performance degradation when deployed in real-world scenarios involving acoustic domain shifts, such as background noise and speaker accents. Test-time adaptation (TTA) has recently emerged as…

Acoustic scene classification (ASC) and sound event detection (SED) are major topics in environmental sound analysis. Considering that acoustic scenes and sound events are closely related to each other, the joint analysis of acoustic scenes…

As speech synthesis systems continue to make remarkable advances in recent years, the importance of robust deepfake detection systems that perform well in unseen systems has grown. In this paper, we propose a novel adaptive centroid shift…

Human voices can be used to authenticate the identity of the speaker, but the automatic speaker verification (ASV) systems are vulnerable to voice spoofing attacks, such as impersonation, replay, text-to-speech, and voice conversion.…

The attention-based Transformers have been increasingly applied to audio classification because of their global receptive field and ability to handle long-term dependency. However, the existing frameworks which are mainly extended from the…

Traditionally, adaptive filters have been deployed to achieve AEC by estimating the acoustic echo response using algorithms such as the Normalized Least-Mean-Square (NLMS) algorithm. Several approaches have been proposed over recent years…