Related papers: Generalizable speech deepfake detection via meta-l…

Although Large Language Models (LLMs) have shown promise for human-like conversations, they are primarily pre-trained on text data. Incorporating audio or video improves performance, but collecting large-scale multimodal data and…

We introduce DAS (Domain Adaptation with Synthetic data), a novel domain adaptation framework for pre-trained ASR model, designed to efficiently adapt to various language-defined domains without requiring any real data. In particular, DAS…

Unsupervised domain adaptation (UDA) aims to transfer the knowledge from the labeled source domain to the unlabeled target domain. Existing self-training based UDA approaches assign pseudo labels for target data and treat them as ground…

Fake audio attack becomes a major threat to the speaker verification system. Although current detection approaches have achieved promising results on dataset-specific scenarios, they encounter difficulties on unseen spoofing data.…

Recent advancements in training paradigms for Large Language Models (LLMs) have unlocked their remarkable capabilities in natural language processing and cross-domain generalization. While LLMs excel in tasks like programming and…

Low-Rank Adapters (LoRAs) have transformed the fine-tuning of Large Language Models (LLMs) by enabling parameter-efficient updates. However, their widespread adoption remains limited by the reliance on GPU-based training. In this work, we…

In recent years, self-supervised learning (SSL) models have made significant progress in audio deepfake detection (ADD) tasks. However, existing SSL models mainly rely on large-scale real speech for pre-training and lack the learning of…

The ASVspoof 2021 benchmark, a widely-used evaluation framework for anti-spoofing, consists of two subsets: Logical Access (LA) and Deepfake (DF), featuring samples with varied coding characteristics and compression artifacts. Notably, the…

Low-Rank Adaptation (LoRA) has emerged as one of the most widely used parameter-efficient fine-tuning (PEFT) methods for adapting large language models (LLMs) to downstream tasks. While highly effective in single-task settings, it struggles…

Low-Rank Adaptation (LoRA) is widely used for parameter-efficient fine-tuning of large language models, but it is notably ineffective at removing backdoor behaviors from poisoned pretrained models when fine-tuning on clean dataset. Contrary…

The rise of highly convincing synthetic speech poses a growing threat to audio communications. Although existing Audio Deepfake Detection (ADD) methods have demonstrated good performance under clean conditions, their effectiveness drops…

Speaker diarisation systems nowadays use embeddings generated from speech segments in a bottleneck layer, which are needed to be discriminative for unseen speakers. It is well-known that large-margin training can improve the generalisation…

Automatic Speaker Verification systems are gaining popularity these days; spoofing attacks are of prime concern as they make these systems vulnerable. Some spoofing attacks like Replay attacks are easier to implement but are very hard to…

Fine-tuning pre-trained large language models in a parameter-efficient manner is widely studied for its effectiveness and efficiency. LoRA is one of the most widely used methods, which assumes that the optimization process is essentially…

Audio deepfake detection has become increasingly challenging due to rapid advances in speech synthesis and voice conversion technologies, particularly under channel distortions, replay attacks, and real-world recording conditions. This…

Fine-tuning is widely used to tailor large language models for specific tasks such as neural machine translation (NMT). However, leveraging transfer learning is computationally expensive when fine-tuning large multilingual models with…

In fine-tuning large language models (LLMs), conserving computational resources while maintaining effectiveness and improving outcomes within the same computational constraints is crucial. The Low-Rank Adaptation (LoRA) strategy balances…

Automatic Speech Recognition (ASR) in dialect-heavy settings remains challenging due to strong regional variation and limited labeled data. We propose GLoRIA, a parameter-efficient adaptation framework that leverages metadata (e.g.,…

Adapting deep learning models to new domains often requires computationally intensive retraining and risks catastrophic forgetting. While fine-tuning enables domain-specific adaptation, it can reduce robustness to distribution shifts,…

The performance of spoofing countermeasure systems depends fundamentally upon the use of sufficiently representative training data. With this usually being limited, current solutions typically lack generalisation to attacks encountered in…