Audio Embedding-Aware Dialogue Policy Learning

Autor: Asier Lopez Zorrilla, Maria Ines Torres, Heriberto Cuayahuitl

Following the success of Natural Language Processing (NLP) transformers pretrained via self-supervised learning, similar models have been proposed recently for speech processing such as Wav2Vec2, HuBERT and UniSpeech-SAT. An interesting yet unexplore

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::a6d2d9d009d532f7c8e756a9d4f8cdc5
https://eprints.lincoln.ac.uk/id/eprint/52689/1/Audio_Embedding-Aware_Dialogue_Policy_Learning.pdf

Strategic Dialogue Management via Deep Reinforcement Learning

Autor: Heriberto Cuayahuitl, Simon Keizer, Oliver Lemon

Publikováno v: Heriot-Watt University

Artificially intelligent agents equipped with strategic skills that can negotiate during their interactions with other natural or artificial agents are still underdeveloped. This paper describes a successful application of Deep Reinforcement Learning

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::521e1ca68aa7eb2e28496a4058d9bf8b

Multimodal Child-Robot Interaction: Building Social Bonds

Autor: Tony Belpaeme, Paul Baxter, Robin Read, Rachel Wood Heriberto Cuayahuitl, Bernd Kiefer, Stefania Racioppa, Ivana Kruijff-Korbayov?a Georgios Athanasopoulos, Valentin Enescu Rosemarijn Looije, Mark Neerincx Yiannis Demiris, Raquel Ros-Espinoza Aryel Beck, Lola Canamero, Antione Hiolle, Matthew Lewis Ilaria Baroni, Marco Nalin Piero Cosi, Giulio Paci, Fabio Tesser, Giacomo Sommavilla Remi Humbert

Publikováno v: Journal of Human-Robot Interaction 1 (2012): 33–53.
info:cnr-pdr/source/autori:Tony Belpaeme, Paul Baxter, Robin Read, Rachel Wood Heriberto Cuayahuitl, Bernd Kiefer, Stefania Racioppa, Ivana Kruijff-Korbayov?a Georgios Athanasopoulos, Valentin Enescu Rosemarijn Looije, Mark Neerincx Yiannis Demiris, Raquel Ros-Espinoza Aryel Beck, Lola Canamero, Antione Hiolle, Matthew Lewis Ilaria Baroni, Marco Nalin Piero Cosi, Giulio Paci, Fabio Tesser, Giacomo Sommavilla Remi Humbert/titolo:Multimodal Child-Robot Interaction: Building Social Bonds/doi:/rivista:Journal of Human-Robot Interaction/anno:2012/pagina_da:33/pagina_a:53/intervallo_pagine:33–53/volume:1

For robots to interact effectively with human users they must be capable of coordinated, timely behavior in response to social context. The Adaptive Strategies for Sustainable Long-Term Social Interaction (ALIZ-E) project focuses on the design of lon

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=cnr_________::9a7f93702b805ed13760839b138a8e81
http://www.cnr.it/prodotto/i/210340