12 citations · 33 across the 11 of their papers we have counts for
Showing cs.SDShow all
2 papers · 1 filter
cs.SD2022
Generative Data Augmentation Guided by Triplet Loss for Speech Emotion Recognition
Shijun Wang, Hamed Hemati, Jón Guðnason +1
Speech Emotion Recognition (SER) is crucial for human-computer interaction but still remains a challenging problem because of two major obstacles: data scarcity and imbalance. Many…
cs.SD2020★ 2 cited
Using IPA-Based Tacotron for Data Efficient Cross-Lingual Speaker Adaptation and Pronunciation Enhancement
Hamed Hemati, Damian Borth
Recent neural Text-to-Speech (TTS) models have been shown to perform very well when enough data is available. However, fine-tuning them for new speakers or languages is not straigh…