Year: 2013
Type: conference-paper
Abstract: Emotion in speech is an important and challenging research area. Addition or understanding of emotions from speech is challenging. But an equally difficult task is to identify the in-tended emotion from an audio or speech. Understanding emo-tions is important not only in itself as a research area, but also, for adding emotions to synthesized speech. Evaluating synthe-sized speech with emotions can be simplified if the correct fac-tors in emotion perception can be first identified. To this end, this work explores various factors that could influence the per-ception of emotions. These factors include semantic informa-tion of the text, contextual information, language understand-ing and knowledge. This work also investigates the right frame-work for a subjective perceptual evaluation by providing dif-ferent options to the listeners and checking which ones among these are the most effective response to evaluate the perception of the emotion. Index Terms: Emotion perception, perceptual factors, emo-tions in speech, emotional speech analysis/synthesis, metrics for subjective perceptual evaluations 1.
Authors: Lakshmi Babu Saheer, Blaise Potard
Institution: Idiap Research Institute
Language: English
Topic: Emotion and Mood Recognition
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
Funder: Eurostars
OpenAlex ID: W1598284903