K. Dai, H.J. Fell, and J. MacAuslan (USA)
Voice recognition software, emotion recognition, speech
landmarks, neural networks
Emotion recognition is an important factor of affective
computing and has potential use in assistive technologies.
In this paper we used landmark and other acoustic
features to recognize different emotional states in speech.
We analyzed 2442 utterances from the Emotional Prosody
Speech and Transcripts corpus and extracted 62 features
from each utterance. A neural network classifier was built
to recognize different emotional states of these utterances.
We obtained over 90% accuracy in distinguishing hot
anger and neutral states, over 80% accuracy in
distinguishing happy and sadness as well as in
distinguishing hot anger and cold anger. We also
achieved 62% and 49% accuracy for classifying 4 and 6
emotions respectively. We had 20% accuracy in
classifying all 15 emotions in the corpus which is a large
improvement over other studies. We plan to apply our
work to developing a tool to help people who have
difficulty in identifying emotion.