Sarala Padi
Papers
2
Total Citations
62
H-Index
2
About
Sarala Padi is an emerging researcher specializing in multimodal emotion recognition and affective computing, with a focus on advancing the emotional intelligence of artificial intelligence systems. Her work sits at the compelling intersection of speech processing, natural language understanding, and deep learning, where she investigates how machines can better perceive and interpret human emotional states. Padi's most notable contribution centers on leveraging transfer learning techniques — drawing from speaker recognition models and BERT-based language frameworks — to build robust multimodal emotion recognition systems. This research, which has garnered over 60 citations across related publications since 2022, addresses a critical challenge in human-computer interaction: enabling AI to respond not just to what people say, but *how* they feel when saying it. Her work has practical implications across diverse real-world applications, including customer behavior analysis in call centers, gaming environments, and intelligent personal assistants. By combining acoustic and textual modalities through transfer learning, Padi has helped demonstrate that pre-trained models can be effectively repurposed for emotion-aware AI systems, reducing the need for large labeled emotional datasets. Her contributions represent meaningful progress toward more empathetic and context-aware next-generation AI technologies.
Research Focus
Key Achievements
Top Papers
- 1
- 2