3 papers
cs.CL2026
FLiP: Towards understanding and interpreting multimodal multilingual sentence embeddings
Santosh Kesiraju, Bolaji Yusuf, Å imon SedláÄek +2
This paper presents factorized linear projection (FLiP) models for understanding pretrained sentence embedding spaces. We train FLiP models to recover the lexical content from mult…
eess.AS2026
Endpoint Anticipation for Low-Latency Spoken Dialogue
Sathvik Udupa, Shinji Watanabe, Petr Schwarz +1
While low-latency interaction is critical for spoken dialogue, cascaded architectures are often bottlenecked by reactive turn-completion detection. We propose Endpoint Anticipation…
cs.SD2025
Streaming Endpointer for Spoken Dialogue using Neural Audio Codecs and Label-Delayed Training
Sathvik Udupa, Shinji Watanabe, Petr Schwarz +1
Accurate, low-latency endpointing is crucial for effective spoken dialogue systems. While traditional endpointers often rely on spectrum-based audio features, this work proposes re…