Zobrazeno 1 - 10
of 13
pro vyhledávání: '"Eunjoon Cho"'
Autor:
Andrea Madotto, Zhaojiang Lin, Zhenpeng Zhou, Seungwhan Moon, Paul Crook, Bing Liu, Zhou Yu, Eunjoon Cho, Pascale Fung, Zhiguang Wang
Publikováno v:
Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing.
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::31bdb78c6feed45eecc03ef9e8128d8c
https://doi.org/10.18653/v1/2021.emnlp-main.590
https://doi.org/10.18653/v1/2021.emnlp-main.590
Autor:
Rajen Subba, Seungwhan Moon, Eunjoon Cho, Zhiguang Wang, Zhenpeng Zhou, Bing Liu, Zhaojiang Lin, Paul A. Crook, Andrea Madotto, Zhou Yu
Publikováno v:
NAACL-HLT
Zero-shot cross-domain dialogue state tracking (DST) enables us to handle unseen domains without the expense of collecting in-domain data. In this paper, we propose a slot descriptions enhanced generative approach for zero-shot cross-domain DST. Spec
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::9e953f909cda8f6296ba3a93a4182439
https://doi.org/10.18653/v1/2021.naacl-main.448
https://doi.org/10.18653/v1/2021.naacl-main.448
Autor:
Shivani Poddar, Theodore Levin, Paul A. Crook, David Whitney, Satwik Kottur, Seungwhan Moon, Ankita De, Ahmad Beirami, Rajen Subba, Eunjoon Cho, Daniel Difranco, Alborz Geramifard
Publikováno v:
COLING
Next generation virtual assistants are envisioned to handle multimodal inputs (e.g., vision, memories of previous interactions, in addition to the user's utterances), and perform multimodal actions (e.g., displaying a route in addition to generating
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::39d921acdca771360210c88125100528
https://doi.org/10.18653/v1/2020.coling-main.96
https://doi.org/10.18653/v1/2020.coling-main.96
Autor:
Stephen Roller, Eunjoon Cho, Claire Cardie, Seungwhan Moon, Paul A. Crook, Becka Silvert, Bing Liu, Kai Sun, Honglei Liu, Zhiguang Wang
Publikováno v:
NAACL-HLT
Existing dialogue corpora and models are typically designed under two disjoint motives: while task-oriented systems focus on achieving functional goals (e.g., booking hotels), open-domain chatbots aim at making socially engaging conversations. In thi
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::95890797653ccbee818f5846ed062193
Autor:
Shankar Kumar, Eunjoon Cho
Publikováno v:
ICASSP
Speech recognition in digital assistants such as Google Assistant can potentially benefit from the use of conversational context consisting of user queries and responses from the agent. We explore the use of recurrent, Long Short-Term Memory (LSTM),
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::76aef3a1df3b26fbb5e22e7ae9aba98e
https://doi.org/10.1109/icassp.2018.8462279
https://doi.org/10.1109/icassp.2018.8462279
Publikováno v:
ICASSP
Standard automatic speech recognition (ASR) systems are increasingly expected to recognize foreign entities, yet doing so while preserving accuracy on native words remains a challenge. We describe a novel approach for recognizing foreign words by inj
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::37e29ae83c179ffc897a16f81909f552
https://doi.org/10.1109/icassp.2018.8461600
https://doi.org/10.1109/icassp.2018.8461600
Autor:
Francoise Beaufays, Kaisuke Nakajima, Keith Hall, Cyril Allauzen, Eunjoon Cho, Linda Zhang, Brian Roark, Michael Riley, David Rybach, Noah Coccaro
Publikováno v:
INTERSPEECH
We introduce a technique for dynamically applying contextually-derived language models to a state-of-the-art speech recognition system. These generally small-footprint models can be seen as a generalization of cache-based models [1], whereby contextu
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::66389e512319caefd99454128c56aeac
https://doi.org/10.21437/interspeech.2015-340
https://doi.org/10.21437/interspeech.2015-340
Publikováno v:
INTERSPEECH
Scopus-Elsevier
Scopus-Elsevier
Trying to automatically detect laughter and other nonlinguistic events in speech raises a fundamental question: Is it appropriate to simply adopt acoustic features that have traditionally been used for analyzing linguistic events? Thus we take a step
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::e407ca5a7fb971fe5ba0faac8725ee8e
https://doi.org/10.21437/interspeech.2013-58
https://doi.org/10.21437/interspeech.2013-58
Publikováno v:
ICASSP
We provide a single channel speech enhancement method leveraging the harmonic structure of voiced speech. A sinusoidal model, based on the pitch of the speaker, is used to filter noisy speech and remove any noise components that lie between the harmo
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::50ffc54a3dd04dc8663184d573e8fb8d
https://doi.org/10.1109/icassp.2012.6288935
https://doi.org/10.1109/icassp.2012.6288935
Publikováno v:
KDD
Even though human movement and mobility patterns have a high degree of freedom and variation, they also exhibit structural patterns due to geographic and social constraints. Using cell phone location data, as well as data from two online location-bas
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::4f556aa6f2f8886e6f495f3d3b418c60
https://doi.org/10.1145/2020408.2020579
https://doi.org/10.1145/2020408.2020579