Dialogue Utterance
Dialogue utterance research focuses on understanding and modeling the complexities of conversational exchanges, aiming to improve human-computer interaction and AI capabilities. Current research emphasizes developing models that accurately capture nuances like personality, emotion, and uncertainty in dialogue, often leveraging large language models (LLMs) and contrastive learning techniques for improved performance. This work is significant for advancing AI's ability to engage in natural, contextually aware conversations, with applications ranging from improved chatbots and virtual assistants to more effective tools for healthcare and education.
Papers
Task Oriented Dialogue as a Catalyst for Self-Supervised Automatic Speech Recognition
David M. Chan, Shalini Ghosh, Hitesh Tulsiani, Ariya Rastrow, Björn Hoffmeister
Are LLMs Robust for Spoken Dialogues?
Seyed Mahed Mousavi, Gabriel Roccabruna, Simone Alghisi, Massimo Rizzoli, Mirco Ravanelli, Giuseppe Riccardi