Current Challenges in Spoken Dialogue Systems and Why they are Critical for Healthcare Applications. Addlesee, A., Konstas, I., & Eshghi, A. In Proceedings of the Dialogue for Good (DiGo) 2019 workshop, 2019. abstract bibtex Dialogue technology such as Amazon's Alexa has the potential to transform the healthcare industry. However, current systems are not yet naturally interactive: they are often turn-based, have naive end-of-turn detection and completely ignore many types of verbal and visual feedback - such as backchannels, hesitation markers, filled pauses, gaze, brow furrows & disfluencies - that are crucial in guiding & managing the conversational process. This is especially important in the healthcare industry as target users of Spoken Dialogue Systems (SDS) are likely to be frail, older, distracted, or suffer from cognitive decline, which impact their ability to make effective use of current systems. In this paper, we outline some of the challenges that are in urgent need of further research, including Incremental Speech Recognition, Natural Language Understanding and a systematic study of the interactional patterns in conversation that are potentially diagnostic of Dementia, and how these might inform research on and the design of the next generation of SDSs.
@inproceedings{
title = {Current Challenges in Spoken Dialogue Systems and Why they are Critical for Healthcare Applications},
type = {inproceedings},
year = {2019},
city = {Stockholm, Sweden},
id = {0221973b-2f4b-3fd5-845a-89f321fd5676},
created = {2019-08-16T08:41:19.724Z},
file_attached = {false},
profile_id = {d7d2e6da-aa5b-3ab3-b3f2-a5350adf574a},
last_modified = {2019-08-16T08:41:19.724Z},
read = {false},
starred = {false},
authored = {true},
confirmed = {true},
hidden = {false},
citation_key = {Addlesee.etal19},
private_publication = {false},
abstract = {Dialogue technology such as Amazon's Alexa has the potential to transform the healthcare industry. However, current systems are not yet naturally interactive: they are often turn-based, have naive end-of-turn detection and completely ignore many types of verbal and visual feedback - such as backchannels, hesitation markers, filled pauses, gaze, brow furrows & disfluencies - that are crucial in guiding & managing the conversational process. This is especially important in the healthcare industry as target users of Spoken Dialogue Systems (SDS) are likely to be frail, older, distracted, or suffer from cognitive decline, which impact their ability to make effective use of current systems. In this paper, we outline some of the challenges that are in urgent need of further research, including Incremental Speech Recognition, Natural Language Understanding and a systematic study of the interactional patterns in conversation that are potentially diagnostic of Dementia, and how these might inform research on and the design of the next generation of SDSs.},
bibtype = {inproceedings},
author = {Addlesee, Angus and Konstas, Ioannis and Eshghi, Arash},
booktitle = {Proceedings of the Dialogue for Good (DiGo) 2019 workshop}
}
Downloads: 0
{"_id":"f5aJJxspdY7o5yXjY","bibbaseid":"addlesee-konstas-eshghi-currentchallengesinspokendialoguesystemsandwhytheyarecriticalforhealthcareapplications-2019","author_short":["Addlesee, A.","Konstas, I.","Eshghi, A."],"bibdata":{"title":"Current Challenges in Spoken Dialogue Systems and Why they are Critical for Healthcare Applications","type":"inproceedings","year":"2019","city":"Stockholm, Sweden","id":"0221973b-2f4b-3fd5-845a-89f321fd5676","created":"2019-08-16T08:41:19.724Z","file_attached":false,"profile_id":"d7d2e6da-aa5b-3ab3-b3f2-a5350adf574a","last_modified":"2019-08-16T08:41:19.724Z","read":false,"starred":false,"authored":"true","confirmed":"true","hidden":false,"citation_key":"Addlesee.etal19","private_publication":false,"abstract":"Dialogue technology such as Amazon's Alexa has the potential to transform the healthcare industry. However, current systems are not yet naturally interactive: they are often turn-based, have naive end-of-turn detection and completely ignore many types of verbal and visual feedback - such as backchannels, hesitation markers, filled pauses, gaze, brow furrows & disfluencies - that are crucial in guiding & managing the conversational process. This is especially important in the healthcare industry as target users of Spoken Dialogue Systems (SDS) are likely to be frail, older, distracted, or suffer from cognitive decline, which impact their ability to make effective use of current systems. In this paper, we outline some of the challenges that are in urgent need of further research, including Incremental Speech Recognition, Natural Language Understanding and a systematic study of the interactional patterns in conversation that are potentially diagnostic of Dementia, and how these might inform research on and the design of the next generation of SDSs.","bibtype":"inproceedings","author":"Addlesee, Angus and Konstas, Ioannis and Eshghi, Arash","booktitle":"Proceedings of the Dialogue for Good (DiGo) 2019 workshop","bibtex":"@inproceedings{\n title = {Current Challenges in Spoken Dialogue Systems and Why they are Critical for Healthcare Applications},\n type = {inproceedings},\n year = {2019},\n city = {Stockholm, Sweden},\n id = {0221973b-2f4b-3fd5-845a-89f321fd5676},\n created = {2019-08-16T08:41:19.724Z},\n file_attached = {false},\n profile_id = {d7d2e6da-aa5b-3ab3-b3f2-a5350adf574a},\n last_modified = {2019-08-16T08:41:19.724Z},\n read = {false},\n starred = {false},\n authored = {true},\n confirmed = {true},\n hidden = {false},\n citation_key = {Addlesee.etal19},\n private_publication = {false},\n abstract = {Dialogue technology such as Amazon's Alexa has the potential to transform the healthcare industry. However, current systems are not yet naturally interactive: they are often turn-based, have naive end-of-turn detection and completely ignore many types of verbal and visual feedback - such as backchannels, hesitation markers, filled pauses, gaze, brow furrows & disfluencies - that are crucial in guiding & managing the conversational process. This is especially important in the healthcare industry as target users of Spoken Dialogue Systems (SDS) are likely to be frail, older, distracted, or suffer from cognitive decline, which impact their ability to make effective use of current systems. In this paper, we outline some of the challenges that are in urgent need of further research, including Incremental Speech Recognition, Natural Language Understanding and a systematic study of the interactional patterns in conversation that are potentially diagnostic of Dementia, and how these might inform research on and the design of the next generation of SDSs.},\n bibtype = {inproceedings},\n author = {Addlesee, Angus and Konstas, Ioannis and Eshghi, Arash},\n booktitle = {Proceedings of the Dialogue for Good (DiGo) 2019 workshop}\n}","author_short":["Addlesee, A.","Konstas, I.","Eshghi, A."],"biburl":"https://bibbase.org/service/mendeley/d7d2e6da-aa5b-3ab3-b3f2-a5350adf574a","bibbaseid":"addlesee-konstas-eshghi-currentchallengesinspokendialoguesystemsandwhytheyarecriticalforhealthcareapplications-2019","role":"author","urls":{},"metadata":{"authorlinks":{}}},"bibtype":"inproceedings","biburl":"https://bibbase.org/service/mendeley/d7d2e6da-aa5b-3ab3-b3f2-a5350adf574a","dataSources":["TcQYToyGTfqDApS68","gQ3XnmcCc7p5JYvBa","pB6WyiWKHxyFpemKA"],"keywords":[],"search_terms":["current","challenges","spoken","dialogue","systems","critical","healthcare","applications","addlesee","konstas","eshghi"],"title":"Current Challenges in Spoken Dialogue Systems and Why they are Critical for Healthcare Applications","year":2019}