Mean Opinion Score: 4.08
Papers with Code · CC BY-SA 4.0
Speech Synthesis
Speech synthesis is the task of generating speech from some other modality like text, lip movements etc.
Please note that the leaderboards here are not really comparable between studies - as they use mean opinion score as a metric and collect different samples from Amazon Mechnical Turk.
<span style="color:grey; opacity: 0.6">( Image credit: WaveNet: A generative model for raw audio )</span>
논문
PESQ: 4.362MCD: 0.2903Periodicity: 0.0593V/UV F1: 0.9793
PESQ: 4.120MCD: 0.4129Periodicity: 0.0924V/UV F1: 0.9644
PESQ: 4.3536Periodicity: 0.0751V/UV F1: 0.9745M-STFT: 0.7982
Mean Opinion Score: 4.526
Mean Opinion Score: 3.24
NLL: 1.387
PESQ: 4.454Periodicity: 0.0528V/UV F1: 0.9756M-STFT: 0.7358
Mean Opinion Score: 4.48
Mean Opinion Score: 4.44
PESQ: 2.947MCD: 0.6603Periodicity: 0.1565V/UV F1: 0.9300
Mean Opinion Score: 0
PESQ: 4.248Periodicity: 0.0765V/UV F1: 0.9651M-STFT: 1.0269
PESQ: 4.228Periodicity: 0.090V/UV F1: 0.968
Mean Opinion Score: 4.001
PESQ: 3.70Periodicity: 0.101V/UV F1: 0.9582
PESQ: 3.027MCD: 1.2455Periodicity: 0.1416V/UV F1: 0.9410
PESQ: 3.138MCD: 2.3591Periodicity: 0.1485V/UV F1: 0.9378