MMIU: Dataset for Visual Intent Understanding in Multimodal Assistants

no code implementations • 13 Oct 2021 • Alkesh Patel, Joel Ruben Antony Moniz, Roman Nguyen, Nick Tzou, Hadas Kotek, Vincent Renkens

In multimodal assistant, where vision is also one of the input modalities, the identification of user intent becomes a challenging task as visual input can influence the outcome.

intent-classification Intent Classification +4

User-Initiated Repetition-Based Recovery in Multi-Utterance Dialogue Systems

no code implementations • 2 Aug 2021 • Hoang Long Nguyen, Vincent Renkens, Joris Pelemans, Srividya Pranavi Potharaju, Anil Kumar Nalamalapu, Murat Akbacak

In this paper, we attempt to bridge this gap and present a system that allows a user to correct speech recognition errors in a virtual assistant by repeating misunderstood words.

speech-recognition Speech Recognition

State Gradients for RNN Memory Analysis

no code implementations • WS 2018 • Lyan Verwimp, Hugo Van hamme, Vincent Renkens, Patrick Wambacq

We present a framework for analyzing what the state in RNNs remembers from its input embeddings.