Post-Doctoral Research Visit F/M Deep generative models for robust and generalizable audio-visual speech enhancement

This postdoctoral research is part of the REAVISE project: “Robust and Efficient Deep Learning based Audiovisual Speech Enhancement” (2023-2026) funded by the French National Research Agency (ANR). The general objective of REAVISE is to develop a unified audio-visual speech enhancement (AVSE) framework. This will leverage recent breakthroughs in statistical signal processing, machine learning, and deep neural networks to create a robust and efficient AVSE system.

Starting date & duration: October 2024 (flexible), for two years.

Background. Audio-visual speech enhancement (AVSE) aims to improve the intelligibility and quality of noisy speech signals by utilizing complementary visual information, such as the lip movements of the speaker [1]. This technique is especially useful in highly noisy environments. The advent of deep neural network (DNN) architectures has led to significant advancements in AVSE, prompting extensive research into the area [1]. Existing DNN-based AVSE methods are divided into supervised and unsupervised approaches. In supervised approaches, a DNN is trained on a large audiovisual corpus, like AVSpeech [2], which includes a wide range of noise conditions. This training enables the DNN to transform noisy speech signals and corresponding video frames into a clean speech estimate. These models are typically complex, containing millions of parameters.

On the other hand, unsupervised methods [3-5] employ statistical modeling combined with DNNs. These methods use deep generative models, such as variational autoencoders (VAEs) [6] and diffusion models [7], trained on clean datasets like TCD-TIMIT [8], to probabilistically estimate clean speech signals. Since these models do not train on noisy data, they are generally lighter than supervised models and may offer better generalization capabilities and robustness to visual noise, as indicated by their probabilistic nature [3-5]. Despite these advantages, unsupervised methods remain less explored compared to their supervised counterparts.

Objectives. In this project, we aim to develop a robust and efficient AVSE framework by thoroughly exploring the integration of recent deep-learning architectures designed for speech enhancement, encompassing both supervised and unsupervised approaches. Our goal is to leverage the strengths of both strategies alongside cutting-edge generative modeling techniques to bridge their gap. This includes the implementation of computationally efficient multimodal (latent) diffusion models, dynamical VAEs [9], temporal convolutional networks (TCNs) [10], and attention-based methods [11]. The main objectives of the project are outlined as follows:

1. Develop a neural architecture that assesses the reliability of lip images—whether they are frontal, non-frontal, occluded, in extreme poses, or missing—by providing a normalized reliability score at the output [12];
2. Design deep generative models that efficiently exploit the sequential nature of data and effectively fuse audio-visual features;
3. Integrate the visual reliability analysis network within the deep generative model to selectively use visual data. This will enable a flexible and robust framework for audio-visual fusion and enhancement.

The preferred profile is described below.

• Master's degree, or equivalent, in the field of speech/audio processing, computer vision, machine learning, or in a related field;
• Ability to work independently as well as in a team;
• Solid programming skills (Python, PyTorch) and deep learning knowledge;
• Good level of written and spoken English.

• Subsidized meals
• Partial reimbursement of public transport costs
• Leave: 7 weeks of annual leave + 10 extra days off due to RTT (statutory reduction in working hours) + possibility of exceptional leave (sick children, moving home, etc.)
• Possibility of teleworking (after 6 months of employment) and flexible organization of working hours
• Professional equipment available (videoconferencing, loan of computer equipment, etc.)
• Social, cultural and sports events and activities
• Access to vocational training
• Social security coverage

2788€ gross/month