Paolo Prandoni

Biography

I appeared about at the same time as the White Album and, upon being born, I immediately took the one and only sabbatical of my life, which lasted a leisurely four years. I then proceeded to be pre-schooled, schooled, middle- and high-schooled, college educated, and finally grad-schooled here at EPFL. As a kid I was fascinated by those expensive long-distance phone calls and so I specialized in communication systems. And then I did this and I did that. But do we really want to go into details? I thought so.

Official source

https://people.epfl.ch/paolo.prandoni

About this result

This page is automatically generated and may contain information that is not correct, complete, up-to-date, or relevant to your search query. The same applies to every other page on this website. Please make sure to verify the information with EPFL's official sources.

Related units (3)

Related units

Courses taught by this person (1)

Students learn digital signal processing theory, including discrete time, Fourier analysis, filter design, adaptive filtering, sampling, interpolation and quantization; they are introduced to image processing and data communication system design.

Courses taught by this person

Related research domains (5)

Related research domains

Related publications (27)

Related publications

People doing similar research (87)

People doing similar research

Non-Intrusive Speech Quality Assessment with Transfer Learning and Subject-specific Scaling

Milos Cernak, Natalia Nessler, Paolo Prandoni

In communication systems, it is crucial to estimate the perceived quality of audio and speech. The industrial standards for many years have been PESQ, 3QUEST, and POLQA, which are intrusive methods. This restricts the possibilities of using these metrics in real-world conditions, where we might not have access to the clean reference signal. In this work, we develop a new non-intrusive metric based on crowd-sourced data. We build a new speech dataset by combining publicly available speech, noises, and reverberations. Then we follow the ITU P.808 recommendation to label the dataset with mean opinion scores (MOS). Finally, we train a deep neural network to estimate the MOS from the speech data in a non-intrusive way. We propose two novelties in our work. First, we explore transfer learning by pre-training a model using a larger set of POLQA scores and finetuning with the smaller (and thus cheaper) human-labeled set. Secondly, we perform a subject-specific scaling in the MOS scores to adjust for their different subjective scales. Our model yields better accuracy than PESQ, POLQA, and other non-intrusive methods when evaluated on the independent VCTK test set. We also report misleading POLQA scores for reverberant speech.

ISCA-INT SPEECH COMMUNICATION ASSOC2021

Teaching Practical DSP with Off-the-Shelf Hardware and Free Software

Eric Bezzam, Adrien Guillaume Olivier Hoffet, Paolo Prandoni

In this paper we describe our approach to teaching applied digital signal processing (DSP) using freely-available software and inexpensive off-the-shelf hardware components. The pedagogical framework is built around simple real-time audio processing algorithms that provide immediate and engaging feedback to the students. At the same time, our end goal is to build a learning module that can be easily reproduced by fellow instructors and used in our Massive Open Online Course (MOOC). We use Python for the initial algorithmic prototyping and then transition to a hardware implementation using an STMicroelectronics' Nucleo-64 core with Adafruit I/O breakout boards. We employ modern documentation tools based on Git and Markdown in order to share the material and the exercises, allowing students and educators to access, reproduce, and contribute changes to the content.

IEEE2019

Ieee-Inst Electrical Electronics Engineers Inc2016