SERE is a new semi-supervised method for cross-lingual speech emotion recognition that needs only 5-shot source labels and no target labels or translations by using resonance embeddings and interaction losses.
Self supervised adversarial do- main adaptation for cross-corpus and cross-language speech emotion recognition
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.SD 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Semantic-Emotional Resonance Embedding: A Semi-Supervised Paradigm for Cross-Lingual Speech Emotion Recognition
SERE is a new semi-supervised method for cross-lingual speech emotion recognition that needs only 5-shot source labels and no target labels or translations by using resonance embeddings and interaction losses.