Related papers: Visually Informed Binaural Audio Generation withou…
Variational auto-encoders (VAEs) are deep generative latent variable models that can be used for learning the distribution of complex data. VAEs have been successfully used to learn a probabilistic prior over speech signals, which is then…
High-quality, large-scale data is essential for robust deep learning models in medical applications, particularly ultrasound image analysis. Diffusion models facilitate high-fidelity medical image generation, reducing the costs associated…
To enhance immersive experiences, binaural audio offers spatial awareness of sounding objects in AR, VR, and embodied AI applications. While existing audio spatialization methods can generally map any available monaural audio to binaural…
Piano covers of pop music are enjoyed by many people. However, the task of automatically generating piano covers of pop music is still understudied. This is partly due to the lack of synchronized {Pop, Piano Cover} data pairs, which made it…
Recent advances in image, video, text and audio generative techniques, and their use by the general public, are leading to new forms of content generation. Usually, each modality was approached separately, which poses limitations. The…
Unsupervised image segmentation is a critical task in computer vision. It enables dense scene understanding without human annotations, which is especially valuable in domains where labelled data is scarce. However, existing methods often…
We are witnessing a revolution in conditional image synthesis with the recent success of large scale text-to-image generation methods. This success also opens up new opportunities in controlling the generation and editing process using…
Complex image processing and computer vision systems often consist of a processing pipeline of functional modules. We intend to replace parts or all of a target pipeline with deep neural networks to achieve benefits such as increased…
Data-driven approaches to assist operating room (OR) workflow analysis depend on large curated datasets that are time consuming and expensive to collect. On the other hand, we see a recent paradigm shift from supervised learning to…
Neural networks have recently become the dominant approach to sound separation. Their good performance relies on large datasets of isolated recordings. For speech and music, isolated single channel data are readily available; however the…
Recent advances in unsupervised learning have highlighted the possibility of learning to reconstruct signals from noisy and incomplete linear measurements alone. These methods play a key role in medical and scientific imaging and sensing,…
We present a joint audio-visual model for isolating a single speech signal from a mixture of sounds such as other speakers and background noise. Solving this task using only audio as input is extremely challenging and does not provide an…
Supervised learning is a mainstream approach to audio signal enhancement (SE) and requires parallel training data consisting of both noisy signals and the corresponding clean signals. Such data can only be synthesised and are mismatched…
We introduce and define a novel task-Scene-Aware Visually-Driven Speech Synthesis, aimed at addressing the limitations of existing speech generation models in creating immersive auditory experiences that align with the real physical world.…
Stereo image and video generation, stereo geometry estimation, and condition-controlled view synthesis require paired data in which the variables that determine binocular geometry -- camera baseline, intrinsics, scene depth, and camera…
This work presents self-supervised learning methods for developing monaural speaker-specific (i.e., personalized) speech enhancement models. While generalist models must broadly address many speakers, specialist models can adapt their…
Recent advances in using language models to obtain cross-modal audio-text representations have overcome the limitations of conventional training approaches that use predefined labels. This has allowed the community to make progress in tasks…
To improve speech intelligibility and speech quality in noisy environments, binaural noise reduction algorithms for head-mounted assistive listening devices are of crucial importance. Several binaural noise reduction algorithms such as the…
The recent breakthroughs in natural language processing for model pretraining on large quantities of data have opened the way for similar foundation models in computer vision. These models could greatly simplify the use of images in any…
The task of few-shot visual dubbing focuses on synchronizing the lip movements with arbitrary speech input for any talking head video. Albeit moderate improvements in current approaches, they commonly require high-quality homologous data…