Haljan Lugo Girao, M.Sc.

Forschungsgebiete

• Deep Learning
• Akustische Echokompensation

Abschlussarbeiten

Comparing Flow Matching and Diffusion Techniques for Speech Enhancement Systems
Flow matching provides a promising generalization of diffusion-based generative approaches. Thus, recent state-of-the-art image generation models motivate the adoption of flow matching for speech enhancement tasks like acoustic echo cancellation or noise reduction. In this work, you will explore flow matching and compare it to already established diffusion-based score matching model formulations.

Finding Content-Adaptive Speech Representations via 2D Gaussians
Inspired by recent advances in image compression that leverage Gaussian splatting to achieve extreme compression ratios without sacrificing visual quality, this work investigates the application of similar techniques to speech. You will explore if these techniques translate to the compression of spectrogram representations and assess whether the resulting reconstructions preserve audio fidelity at competitive compression rates.

Exploring Attention Mechanisms for Acoustic Echo Cancellation
Self- and cross-attention are the backbone of modern LLMs and other sequence-to-sequence models. Especially cross-attention may be highly advantageous to model correspondences of the loudspeaker and microphone signal in acoustic echo control (AEC) tasks. In this work, you will investigate the methods to incorporate these attention mechanisms to state-of-the-art AEC systems.

Personalized Acoustic Echo Cancellation
As acoustic echo control (AEC) systems need to extract only the near-end target speaker, which typically does not change on short-term notice, such a system can benefit from a learned speaker embedding. In this work, you will explore possible ways to incorporate these speaker embeddings into an AEC system.