Related papers: Enhancing Self-Supervised Talking Head Forgery Det…

While supervised learning models have shown remarkable performance in various natural language processing (NLP) tasks, their success heavily relies on the availability of large-scale labeled datasets, which can be costly and time-consuming…

Audio-Visual Source Localization (AVSL) aims to locate sounding objects within video frames given the paired audio clips. Existing methods predominantly rely on self-supervised contrastive learning of audio-visual correspondence. Without…

Self-training is an important technique for solving semi-supervised learning problems. It leverages unlabeled data by generating pseudo-labels and combining them with a limited labeled dataset for training. The effectiveness of…

Deepfake detection remains a formidable challenge due to the complex and evolving nature of fake content in real-world scenarios. However, existing academic benchmarks suffer from severe discrepancies from industrial practice, typically…

Unsupervised feature selection (UFS) is widely applied in machine learning and pattern recognition. However, most of the existing methods only consider a single sparsity, which makes it difficult to select valuable and discriminative…

Self-supervised learning has demonstrated impressive performance in speech tasks, yet there remains ample opportunity for advancement in the realm of speech enhancement research. In addressing speech tasks, confining the attention mechanism…

Weakly Supervised Sound Event Detection (WSSED), which relies on audio tags without precise onset and offset times, has become prevalent due to the scarcity of strongly labeled data that includes exact temporal boundaries for events. This…

Controlling the false discovery rate (FDR) in high-dimensional variable selection requires balancing rigorous error control with statistical power. Existing methods with provable guarantees are often overly conservative, creating a…

Semi-supervised object detection (SSOD) aims to boost detection performance by leveraging extra unlabeled data. The teacher-student framework has been shown to be promising for SSOD, in which a teacher network generates pseudo-labels for…

Advances in automatic speaker verification (ASV) promote research into the formulation of spoofing detection systems for real-world applications. The performance of ASV systems can be degraded severely by multiple types of spoofing attacks,…

Automatic speaker verification task has made great achievements using deep learning approaches with the large-scale manually annotated dataset. However, it's very difficult and expensive to collect a large amount of well-labeled data for…

Due to the successful development of deep image generation technology, forgery detection plays a more important role in social and economic security. Racial bias has not been explored thoroughly in the deep forgery detection field. In the…

Speech segmentation at both word and phoneme levels is crucial for various speech processing tasks. It significantly aids in extracting meaningful units from an utterance, thus enabling the generation of discrete elements. In this work we…

Over the last few years, deep learning has grown in popularity for speaker verification, identification, and diarization. Inarguably, a significant part of this success is due to the demonstrated effectiveness of their speaker…

Semi-supervised referring expression segmentation (SS-RES) aims to achieve precise pixel-level language grounding under limited annotation, yet suffers from limited supervision and unreliable pseudo-labels when exploiting unlabeled…

In this work, we develop new self-learning techniques with an attention-based sequence-to-sequence (seq2seq) model for automatic speech recognition (ASR). For untranscribed speech data, the hypothesis from an ASR system must be used as a…

Universal speech enhancement aims at handling inputs with various speech distortions and recording conditions. In this work, we propose a novel hybrid architecture that synergizes the signal fidelity of discriminative modeling with the…

In this paper, we address the hallucination problem commonly found in natural language generation tasks. Language models often generate fluent and convincing content but can lack consistency with the provided source, resulting in potential…

This paper presents a new approach for unsupervised Spoken Term Detection with spoken queries using multiple sets of acoustic patterns automatically discovered from the target corpus. The different pattern HMM configurations(number of…

Recent techniques for speech deepfake detection often rely on pre-trained self-supervised models. These systems, initially developed for Automatic Speech Recognition (ASR), have proved their ability to offer a meaningful representation of…