2 papers
cs.SD2026
CORD-KWS: Calibrated, Order-Aware Detection for Open-Vocabulary Keyword Spotting
Ramesh Gundluru, Adarsh Arigala, Sri Rama Murty Kodukula
Open-vocabulary keyword spotting (KWS) must detect arbitrary keywords without retraining. Cross-attention-based models achieve state-of-the-art performance but require pairwise int…
eess.AS2026
Enhancing Audio Captioning with Auxiliary AudioSet Semantics
Shubham Gupta, Adarsh Arigala, Sri Rama Murty Kodukula
Automatic Audio Captioning (AAC) seeks to generate natural language descriptions of complex acoustic scenes, bridging auditory perception and language understanding. However, word-…