Audio-Visual Speech Enhancement Based on Deep Learning

Daniel Michelsanti

doi:10.54337/aau422930170

Audio-Visual Speech Enhancement Based on Deep Learning

Daniel Michelsanti

Research output: PhD thesis

301 Downloads (Pure)

Original language	English
Supervisors	Tan, Zheng-Hua, Principal supervisor Jensen, Jesper, Co-supervisor
External collaborators	Oticon Danmark AS
Publisher	Aalborg Universitetsforlag
Electronic ISBNs	978-87-7210-698-4
DOIs	https://doi.org/10.54337/aau422930170
Publication status	Published - 2021

Bibliographical note

PhD supervisor:
Professor Zheng-Hua Tan, Aalborg University, Denmark

Assistant PhD supervisor:
Professor Jesper Jensen, Aalborg University, Denmark & Oticon A/S, Denmark

Access to Document

10.54337/aau422930170

PHD_DM_E-pdfFinal published version, 83.4 MB

AUB Link

Search for the material in Aalborg University Library's search engine

Cite this

@misc{b2f8481e0c1647cc8d72c3d2f0c0fa73,

title = "Audio-Visual Speech Enhancement Based on Deep Learning",

author = "Daniel Michelsanti",

note = "PhD supervisor: Professor Zheng-Hua Tan, Aalborg University, Denmark Assistant PhD supervisor: Professor Jesper Jensen, Aalborg University, Denmark & Oticon A/S, Denmark",

year = "2021",

doi = "10.54337/aau422930170",

language = "English",

series = "Ph.d.-serien for Det Tekniske Fakultet for IT og Design, Aalborg Universitet",

publisher = "Aalborg Universitetsforlag",

}

TY - GEN

T1 - Audio-Visual Speech Enhancement Based on Deep Learning

AU - Michelsanti, Daniel

N1 - PhD supervisor: Professor Zheng-Hua Tan, Aalborg University, Denmark Assistant PhD supervisor: Professor Jesper Jensen, Aalborg University, Denmark & Oticon A/S, Denmark

PY - 2021

Y1 - 2021

U2 - 10.54337/aau422930170

DO - 10.54337/aau422930170

M3 - PhD thesis

T3 - Ph.d.-serien for Det Tekniske Fakultet for IT og Design, Aalborg Universitet

PB - Aalborg Universitetsforlag

ER -