Related papers: Adapting Language-Audio Models as Few-Shot Audio L…

Automated Audio Captioning (AAC) aims to generate natural textual descriptions for input audio signals. Recent progress in audio pre-trained models and large language models (LLMs) has significantly enhanced audio understanding and textual…

Large-scale pre-trained Vision-Language models (VLMs), such as CLIP, exhibit strong zero-shot generalization, yet remain highly vulnerable to imperceptible adversarial perturbations, raising serious safety concerns for open-world…

Few-shot semantic segmentation (FSS) aims to segment novel classes in query images using only a small annotated support set. While prior research has mainly focused on improving decoders, the encoder's limited ability to extract meaningful…

Test-time adaptation (TTA) has gained increasing popularity due to its efficacy in addressing ``distribution shift'' issue while simultaneously protecting data privacy. However, most prior methods assume that a paired source domain model…

Recent years have seen increasing concerns about the unsafe response generation of large-scale dialogue systems, where agents will learn offensive or biased behaviors from the real-world corpus. Some methods are proposed to address the…

Through in-context learning (ICL), large-scale language models are effective few-shot learners without additional model fine-tuning. However, the ICL performance does not scale well with the number of available training samples as it is…

Flow-Matching (FM)-based zero-shot text-to-speech (TTS) systems exhibit high-quality speech synthesis and robust generalization capabilities. However, the speaker representation ability of such systems remains underexplored, primarily due…

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…

Recent advances in large pretrained language models have increased attention to zero-shot text classification. In particular, models finetuned on natural language inference datasets have been widely adopted as zero-shot classifiers due to…

This paper presents a novel zero-shot learning approach towards personalized speech enhancement through the use of a sparsely active ensemble model. Optimizing speech denoising systems towards a particular test-time speaker can improve…

We present a novel Speech Augmented Language Model (SALM) with {\em multitask} and {\em in-context} learning capabilities. SALM comprises a frozen text LLM, a audio encoder, a modality adapter module, and LoRA layers to accommodate speech…

In text classification tasks, useful information is encoded in the label names. Label semantic aware systems have leveraged this information for improved text classification performance during fine-tuning and prediction. However, use of…

Currently available benchmarks for few-shot learning (machine learning with few training examples) are limited in the domains they cover, primarily focusing on image classification. This work aims to alleviate this reliance on image-based…

Automated audio captioning models frequently produce overconfident predictions regardless of semantic accuracy, limiting their reliability in deployment. This deficiency stems from two factors: evaluation metrics based on n-gram overlap…

Pre-trained language models (PLMs) have been shown effective for zero-shot (0shot) text classification. 0shot models based on natural language inference (NLI) and next sentence prediction (NSP) employ cross-encoder architecture and infer by…

Audio tagging is an active research area and has a wide range of applications. Since the release of AudioSet, great progress has been made in advancing model performance, which mostly comes from the development of novel model architectures…

Conventional text-to-speech (TTS) research has predominantly focused on enhancing the quality of synthesized speech for speakers in the training dataset. The challenge of synthesizing lifelike speech for unseen, out-of-dataset speakers,…

Audio tagging is the task of predicting the presence or absence of sound classes within an audio clip. Previous work in audio tagging focused on relatively small datasets limited to recognising a small number of sound classes. We…

Speech Emotion Recognition (SER) is fundamental to affective computing and human-computer interaction, yet existing models struggle to generalize across diverse acoustic conditions. While Contrastive Language-Audio Pretraining (CLAP)…

Vision-Language Models (VLMs) such as CLIP enable strong zero-shot recognition but suffer substantial degradation under distribution shifts. Test-Time Adaptation (TTA) aims to improve robustness using only unlabeled test samples, yet most…