Digital Life
Resources provided
The audio dataset will be provided.
Are you interested?
If you are a professor or university student and you are interested in participating in the TUTORING program, register your information so that we can start the program.
Efficient and Accurate Speech Enhancement
The research project is aimed at students with a strong interest in new technologies, especially those related to artificial intelligence techniques applied to speech.
Introduction
The popularity of voice-based interfaces has significantly increased due to their ability to enable hands-free communication with a wide range of devices. In this context, deep learning technologies have emerged as the standard approach to enhance naturalness and efficiency in device interactions.
Edge AI plays a crucial role in the development of such interfaces as it helps to minimize delays and protect user privacy. There are various approaches to improving communication between humans and devices or between humans themselves. One of these approaches involves working at the signal level, which encompasses the speech audio. Typically, this signal is contaminated by the presence of background noise. The task of Speech Enhancement aims to enhance the perceptual intelligibility and quality of speech by effectively removing these unwanted noises.
Challenge Description
- Research the State-of-The-Art about Speech Enhancement
- Exploration and pre-processing of an existing audio dataset: VoiceBank + DEMAND
- Use that data to train and evaluate an efficient and accurate speech-enhancement neural network
- Compare the obtained neural network with other approaches found in the State-of-The-Art
Python programming language and understanding of the fundamentals of machine learning are recommended.
-1.jpg "Fernando López Telefónica")
-10-3.jpg "Jordi Luque Serrano")