Search Results for author:
Found 19 papers, 9 papers with code
Speech inpainting: Context-based speech synthesis guided by video
Audio and visual modalities are inherently connected in speech signals: lip movements and facial expressions are correlated with speech sounds.
A Graph-Based Method for Soccer Action Spotting Using Unsupervised Player Classification
Action spotting in soccer videos is the task of identifying the specific time when a certain key action of the game occurs.
VocaLiST: An Audio-Visual Synchronisation Model for Lips and Voices
Finally, we use the frozen visual features learned by our lip synchronisation model in the singing voice separation task to outperform a baseline audio-visual model which was trained end-to-end.
VoViT: Low Latency Graph-based Audio-Visual Voice Separation Transformer
In a second stage, the predominant voice is enhanced with an audio-only network.
Learning Football Body-Orientation as a Matter of Classification
Orientation is a crucial skill for football players that becomes a differential factor in a large set of events, especially the ones involving passes.
A cappella: Audio-visual Singing Voice Separation
The task of isolating a target singing voice in music videos has useful applications.
Self-Supervised Small Soccer Player Detection and Tracking
In a soccer game, the information provided by detecting and tracking brings crucial clues to further analyze and understand some tactical aspects of the game, including individual and team actions.
Solos: A Dataset for Audio-Visual Music Analysis
In this paper, we present a new dataset of music performance videos which can be used for training machine learning methods for multiple tasks such as audio-visual blind source separation and localization, cross-modal correspondences, cross-modal generation and, in general, any audio-visual selfsupervised task.
Audio Source Separation
Audio-Visual Synchronization
+1
Audio and Speech Processing
Databases
Sound
Using Player's Body-Orientation to Model Pass Feasibility in Soccer
Given a monocular video of a soccer match, this paper presents a computational model to estimate the most feasible pass at any given time.
Conditioned Source Separation for Music Instrument Performances
In music source separation, the number of sources may vary for each piece and some of the sources may belong to the same family of instruments, thus sharing timbral characteristics and making the sources more correlated.
Sound Audio and Speech Processing
Vocoder-Based Speech Synthesis from Silent Videos
Both acoustic and visual information influence human perception of speech.
Multi-channel U-Net for Music Source Separation
However, Conditioned U-Net (C-U-Net) uses a control mechanism to train a single model for multi-source separation and attempts to achieve a performance comparable to that of the dedicated models.
Always Look on the Bright Side of the Field: Merging Pose and Contextual Data to Estimate Orientation of Soccer Players
Although orientation has proven to be a key skill of soccer players in order to succeed in a broad spectrum of plays, body orientation is a yet-little-explored area in sports analytics' research.
Multi-Person tracking by multi-scale detection in Basketball scenarios
The presented system could be used as a source of data gathering in order to extract useful statistics and semantic analyses a posteriori.
A Case Study of Deep-Learned Activations via Hand-Crafted Audio Features
We also propose a technique for measuring the similarity between activation maps and audio features which typically presented in the form of a matrix, such as chromagrams or spectrograms.
Single-Camera Basketball Tracker through Pose and Semantic Feature Fusion
Tracking sports players is a widely challenging scenario, specially in single-feed videos recorded in tight courts, where cluttering and occlusions cannot be avoided.
End-to-End Sound Source Separation Conditioned On Instrument Labels
Can we perform an end-to-end music source separation with a variable number of sources using a deep learning model?
FALDOI: A new minimization strategy for large displacement variational optical flow
We propose a large displacement optical flow method that introduces a new strategy to compute a good local minimum of any optical flow energy functional.
A Computational Model for Amodal Completion
This paper presents a computational model to recover the most likely interpretation of the 3D scene structure from a planar image, where some objects may occlude others.
