Data Augmentation

Disruptive situation detection on public transport through speech emotion recognition
Detecting disruptive situations on public transport by recognizing anger, fear, sadness, and disgust in speech, with small models that stay accurate in noise.
Cite DOI URL
Disruptive situation detection on public transport through speech emotion recognition
Combining WordNet and Word Embeddings in Data Augmentation for Legal Texts
Replacing words in legal sentences with WordNet candidates chosen by GloVe similarity yields synthetic samples that legal experts scored above four alternative methods.
Sezen Perçin, Andrea Galassi, Francesca Lagioia, Federico Ruggeri, Piera Santin, Giovanni Sartor, Paolo Torroni
Cite DOI URL