SEGAA: A Unified Approach to Predicting Age, Gender, and Emotion in Speech.
Aron RIndra SigicharlaChirag PeriwalMohanaprasad KNithya Darisini P. SSourabh TiwariShivani AroraPublished in: CoRR (2024)
Keyphrases
- emotion recognition
- text to speech synthesis
- emotional state
- age groups
- age related
- males and females
- emotional speech
- speech recognition
- male and female
- speech synthesis
- speech signal
- facial expressions
- audio visual
- text to speech
- face recognition
- emotion classification
- recognition engine
- speaker identification
- individual differences
- speaker recognition
- spoken language
- affect sensing
- information retrieval
- pattern recognition
- demographic variables
- automatic speech recognition
- endpoint detection
- statistically significant