Avancerad sökning

Hittade 2 uppsatser som matchar ovanstående sökkriterier.

1. 1. LaMOSNet: Latent Mean-Opinion-Score Network for Non-intrusive Speech Quality Assessment : Deep Neural Network for MOS Prediction

   Master-uppsats, KTH/Skolan för elektroteknik och datavetenskap (EECS)

   Författare :Fredrik Cumlin; [2022]
   Nyckelord :Speech naturalness assessment; Speech quality assessment; Mean opinion score; Voice conversion challenge; Semi-supervised learning; Noisy labels.; Naturligt tal bedömning; Ljudkvalitetsbedömning; Medel bedömningsvärdet; Talkonverteringsutmaningen; Semi-övervakad inlärning; Varierande märkningar.;

   Sammanfattning : Objective non-intrusive speech quality assessment aimed to emulate and correlate with human judgement has received more attention over the years. It is a difficult problem due to three reasons: data scarcity, noisy human judgement, and a potential uneven distribution of bias of mean opinion scores (MOS). LÄS MER

3. 2. Methods for Studying Influence of Io Magma Ocean on Alfvén Wings

   Kandidat-uppsats, KTH/Skolan för elektroteknik och datavetenskap (EECS)

   Författare :Carl Lundquist; Fredrik Cumlin; [2020]
   Nyckelord :Io; magma ocean; Alfv ́en wings; plasma; mag-netic induction;

   Sammanfattning : The most volcanically active body in the solar systemand the innermost Galilean moon of Jupiter, Io, is theorizedto have a global magma ocean beneath it’s surface. Io is alsoin a fast-moving flow of plasma where the moon acts as anobstacle in the flow which generates several complex interactions. LÄS MER