Reverberant Environment
Reverberant environments, characterized by sound reflections that complicate audio signal processing, pose significant challenges for applications like speech recognition and sound source localization. Current research focuses on developing robust algorithms and neural network architectures, such as transformers and convolutional recurrent networks, to address these challenges, often incorporating techniques like spatial filtering, time-frequency analysis, and room impulse response modeling to improve accuracy and efficiency. These advancements are crucial for improving the performance of various technologies, including hearing aids, robotic assistants, and virtual reality systems, by enabling more accurate and reliable audio processing in realistic acoustic settings.
Papers
Analytical model for the relation between signal bandwidth and spatial resolution in Steered-Response Power Phase Transform (SRP-PHAT) maps
Guillermo Garcia-Barrios, Juana M. Gutierrez-Arriola, Nicolas Saenz-Lechon, Victor Jose Osma-Ruiz, Ruben Fraile
Exploiting spatial diversity for increasing the robustness of sound source localization systems against reverberation
Guillermo Garcia-Barrios, Eduardo Latorre Iglesias, Juana M. Gutierrez-Arriola, Ruben Fraile, Nicolas Saenz-Lechon, Victor Jose Osma-Ruiz