Related papers: SG-VAD: Stochastic Gates Based Speech Activity Det…
Speaker verification is hampered by background noise, particularly at extremely low Signal-to-Noise Ratio (SNR) under 0 dB. It is difficult to suppress noise without introducing unwanted artifacts, which adversely affects speaker…
Audio Visual Scene-aware Dialog (AVSD) is the task of generating a response for a question with a given scene, video, audio, and the history of previous turns in the dialog. Existing systems for this task employ the transformers or…
The use of deep networks to extract embeddings for speaker recognition has proven successfully. However, such embeddings are susceptible to performance degradation due to the mismatches among the training, enrollment, and test conditions.…
We introduce SLED, an alternative approach to speech language modeling by encoding speech waveforms into sequences of continuous latent representations and modeling them autoregressively using an energy distance objective. The energy…
Automatic speech quality assessment has raised more attention as an alternative or support to traditional perceptual clinical evaluation. However, most research so far only gains good results on simple tasks such as binary classification,…
Active Speaker Detection (ASD) aims to identify who is currently speaking in each frame of a video. Most state-of-the-art approaches rely on late fusion to combine visual and audio features, but late fusion often fails to capture…
The representation of functions by artificial neural networks depends on a large number of parameters in a non-linear fashion. Suitable parameters of these are found by minimizing a 'loss functional', typically by stochastic gradient…
Audio-visual speech enhancement (AVSE) has been found to be particularly useful at low signal-to-noise (SNR) ratios due to the immunity of the visual features to acoustic noise. However, a significant gap exists in AVSE methods tailored to…
Video Anomaly Detection (VAD) systems can autonomously monitor and identify disturbances, reducing the need for manual labor and associated costs. However, current VAD systems are often limited by their superficial semantic understanding of…
Improving speech system performance in noisy environments remains a challenging task, and speech enhancement (SE) is one of the effective techniques to solve the problem. Motivated by the promising results of generative adversarial networks…
Self-supervised-learning-based pre-trained models for speech data, such as Wav2Vec 2.0 (W2V2), have become the backbone of many speech tasks. In this paper, to achieve speaker diarisation and speech recognition using a single model, a…
Spoofing attacks posed by generating artificial speech can severely degrade the performance of a speaker verification system. Recently, many anti-spoofing countermeasures have been proposed for detecting varying types of attacks from…
Human auditory cortex excels at selectively suppressing background noise to focus on a target speaker. The process of selective attention in the brain is known to contextually exploit the available audio and visual cues to better focus on…
Active authentication refers to a new mode of identity verification in which biometric indicators are continuously tested to provide real-time or near real-time monitoring of an authorized access to a service or use of a device. This is in…
In active speaker detection (ASD), we would like to detect whether an on-screen person is speaking based on audio-visual cues. Previous studies have primarily focused on modeling audio-visual synchronization cue, which depends on the video…
Despite weakly supervised object detection (WSOD) being a promising step toward evading strong instance-level annotations, its capability is confined to closed-set categories within a single training dataset. In this paper, we propose a…
Video anomaly detection (VAD) identifies suspicious events in videos, which is critical for crime prevention and homeland security. In this paper, we propose a simple but highly effective VAD method that relies on attribute-based…
VAD is a critical field in machine learning focused on identifying deviations from normal patterns in images, often challenged by the scarcity of anomalous data and the need for unsupervised training. To accelerate research and deployment…
Low signal-to-noise ratio videos -- such as those from underwater sonar, ultrasound, and microscopy -- pose significant challenges for computer vision models, particularly when paired clean imagery is unavailable. We present Spatiotemporal…
Speaker Identification refers to the process of identifying a person using one's voice from a collection of known speakers. Environmental noise, reverberation and distortion make the task of automatic speaker identification challenging as…