Combining wav2vec2 semantic features, BiVocoder acoustic features, and listener IDs in a multi-task MOS predictor improves system-level naturalness ranking on BVCC while remaining competitive on out-of-domain BC2019.
Common ob- jective evaluation metrics, such as mel-cepstral distance (MCD)
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.SD 1years
2024 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
SAMOS: A Neural MOS Prediction Model Leveraging Semantic Representations and Acoustic Features
Combining wav2vec2 semantic features, BiVocoder acoustic features, and listener IDs in a multi-task MOS predictor improves system-level naturalness ranking on BVCC while remaining competitive on out-of-domain BC2019.