Giovanni Morrone
Speech Technology Scientist at Almawave
Cesena, Emilia-Romagna, Italy
Summary
👤
Senior🎓
Top SchoolGiovanni Morrone is a Speech Technology Scientist with nine years of experience developing deep learning–driven spoken language and audio-visual processing systems for both research and industry. With a PhD-focused expertise in leveraging visual cues (face and lip information) to boost speech robustness in noisy environments, he has driven projects from academic labs to commercial partners like PerVoice and Almawave. His work spans speech enhancement, separation, voice activity detection and diarization, and includes international collaborations such as a visiting researcher stint at Aalborg University. A summa cum laude computer engineering graduate and former postdoc, he blends rigorous academic methods with practical product-minded implementation, having built joint denoising-and-recognition models and contributed to call-center speech analysis efforts. Notably, he pairs deep learning research with hands-on teaching and mentorship, reflecting a commitment to growing both technology and talent.
9 years of coding experience
3 years of employment as a software developer
International Summer School on Deep Learning, International Summer School on Deep Learning at DeepLearn 2018Software Systems, Social Systems, Security and Privacy, Software Systems, Social Systems, Security and Privacy at The Cornell, Maryland, Max Planck Pre-doctoral Research School 2017Master's Degree, Ingegneria Informatica, 110/110 summa cum laude, Master's Degree, Ingegneria Informatica, 110/110 summa cum laude at University of Modena and Reggio EmiliaScientific Lyceum High School "A.Sorbelli" - Pavullo Nel Frignano
Italian, English
Github Skills (12)
face-landmarks10
speech-enhancement9
audio9
speech6
python5
machine-learning4
pytorch4
ai4
multimodal3
deep-learning3
speech-recognition3
kaldi3
Programming languages (1)
Github contributions (5)
dr-pato/audio_visual_speech_enhancement
Oct 2018 - Oct 2022
Face Landmark-based Speaker-Independent Audio-Visual Speech Enhancement in Multi-Talker Environments
Contributions:80 commits, 78 pushes, 1 branch in 3 years 11 months
audioface-landmarksspeech-enhancement
dr-pato/audio-visual-speech-inpainting
Oct 2020 - Oct 2020
Contributions:6 commits, 15 pushes, 1 branch in 26 days
Find and Hire Top DevelopersWe’ve analyzed the programming source code of over 60 million software developers on GitHub and scored them by 50,000 skills. Sign-up on Prog,AI to search for software developers.