Sign Up to like & get
recommendations!
2
Published in 2023 at "IEEE Transactions on Consumer Electronics"
DOI: 10.1109/tce.2023.3236972
Abstract: Conventional Speech Emotion Recognition (SER) approaches put more emphasis on extracting magnitude spectrum-based features, such as Mel Frequency Cepstral Coefficients (MFCCs), and Mel spectrogram. However, phase information is ignored due to signal processing difficulties such…
read more here.
Keywords:
magnitude;
cnn blstm;
phase;
magnitude phase ... See more keywords