REVIEW 2 cited by
CNN+LSTM Architecture for Speech Emotion Recognition with Data Augmentation
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
read the original abstract
In this work we design a neural network for recognizing emotions in speech, using the IEMOCAP dataset. Following the latest advances in audio analysis, we use an architecture involving both convolutional layers, for extracting high-level features from raw spectrograms, and recurrent ones for aggregating long-term dependencies. We examine the techniques of data augmentation with vocal track length perturbation, layer-wise optimizer adjustment, batch normalization of recurrent layers and obtain highly competitive results of 64.5% for weighted accuracy and 61.7% for unweighted accuracy on four emotions.
Forward citations
Cited by 2 Pith papers
-
THAI Speech Emotion Recognition (THAI-SER) corpus
THAI-SER is the first sizeable Thai speech emotion recognition corpus, with 41.6 hours of acted and elicited speech, 27,854 utterances, and crowdsourced labels for five emotions.
-
Explainable Lightweight Compact Deep Models for Speech Emotion Recognition
A 33k-parameter CNN with attentive statistics pooling and Grad-CAM reaches 96.9% accuracy on SAVEE speech emotion recognition, but the evaluation rests on one speaker-independent split.
Discussion (0). Sign in to comment.