A Pilot Evaluation of a Conversational Listener for Conversational User Interfaces

Matthew Peter Aylett; Andrea Carmantini; Christoper J. Pidcock; Eric Nichols; Randy Gomez

doi:10.1145/3571884.3605871

A Pilot Evaluation of a Conversational Listener for Conversational User Interfaces

Matthew Peter Aylett, Andrea Carmantini, Christoper J. Pidcock, Eric Nichols, Randy Gomez

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Abstract

Current spoken conversational user interfaces (CUIs) are predominantly implemented using a sequential, utterance based, two-party, speak-wait/speak-wait approach. Human-human conversation 1) is not sequential, with overlap, interruption and back channels; 2) processes utterances before they are complete and 3) are often multi-party. As part of Honda Research Institute’s Haru project a light weight word spotting speech recognition system - A conversational listener - was implemented to allow very fast turn-taking in simple voice interaction conditions. In this paper, we present a pilot evaluation of the conversational listener in a script follower context (which allows a robot to act out a dialog with a user). We compare a disembodied version of the system with expressive synthesis to Alexa with and without fast turn-taking. Qualitative results indicate that users were sensitive to turn-taking delay and characterful speech synthesis.

Original language	English
Title of host publication	CUI '23: Proceedings of the 5th International Conference on Conversational User Interfaces
Publisher	Association for Computing Machinery
ISBN (Print)	9798400700149
DOIs	https://doi.org/10.1145/3571884.3605871
Publication status	Published - 19 Jul 2023
Event	5th International Conference on Conversational User Interfaces 2023 - Eindhoven, Netherlands Duration: 19 Jul 2023 → 21 Jul 2023

Conference

Conference	5th International Conference on Conversational User Interfaces 2023
Country/Territory	Netherlands
City	Eindhoven
Period	19/07/23 → 21/07/23

Keywords

conversational turn-taking
evaluation
human-machine voice interaction
social robots

ASJC Scopus subject areas

Human-Computer Interaction
Software

Access to Document

10.1145/3571884.3605871

Cite this

@inproceedings{0b12b0444e514cfd911f9b85d1f50102,

title = "A Pilot Evaluation of a Conversational Listener for Conversational User Interfaces",

abstract = "Current spoken conversational user interfaces (CUIs) are predominantly implemented using a sequential, utterance based, two-party, speak-wait/speak-wait approach. Human-human conversation 1) is not sequential, with overlap, interruption and back channels; 2) processes utterances before they are complete and 3) are often multi-party. As part of Honda Research Institute{\textquoteright}s Haru project a light weight word spotting speech recognition system - A conversational listener - was implemented to allow very fast turn-taking in simple voice interaction conditions. In this paper, we present a pilot evaluation of the conversational listener in a script follower context (which allows a robot to act out a dialog with a user). We compare a disembodied version of the system with expressive synthesis to Alexa with and without fast turn-taking. Qualitative results indicate that users were sensitive to turn-taking delay and characterful speech synthesis.",

keywords = "conversational turn-taking, evaluation, human-machine voice interaction, social robots",

author = "Aylett, {Matthew Peter} and Andrea Carmantini and Pidcock, {Christoper J.} and Eric Nichols and Randy Gomez",

year = "2023",

month = jul,

day = "19",

doi = "10.1145/3571884.3605871",

language = "English",

isbn = "9798400700149",

booktitle = "CUI '23: Proceedings of the 5th International Conference on Conversational User Interfaces",

publisher = "Association for Computing Machinery",

address = "United States",

note = "5th International Conference on Conversational User Interfaces 2023 ; Conference date: 19-07-2023 Through 21-07-2023",

}

Aylett, MP, Carmantini, A, Pidcock, CJ, Nichols, E & Gomez, R 2023, A Pilot Evaluation of a Conversational Listener for Conversational User Interfaces. in CUI '23: Proceedings of the 5th International Conference on Conversational User Interfaces., 40, Association for Computing Machinery, 5th International Conference on Conversational User Interfaces 2023, Eindhoven, Netherlands, 19/07/23. https://doi.org/10.1145/3571884.3605871

A Pilot Evaluation of a Conversational Listener for Conversational User Interfaces. / Aylett, Matthew Peter; Carmantini, Andrea; Pidcock, Christoper J. et al.
CUI '23: Proceedings of the 5th International Conference on Conversational User Interfaces. Association for Computing Machinery, 2023. 40.

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

TY - GEN

T1 - A Pilot Evaluation of a Conversational Listener for Conversational User Interfaces

AU - Aylett, Matthew Peter

AU - Carmantini, Andrea

AU - Pidcock, Christoper J.

AU - Nichols, Eric

AU - Gomez, Randy

PY - 2023/7/19

Y1 - 2023/7/19

N2 - Current spoken conversational user interfaces (CUIs) are predominantly implemented using a sequential, utterance based, two-party, speak-wait/speak-wait approach. Human-human conversation 1) is not sequential, with overlap, interruption and back channels; 2) processes utterances before they are complete and 3) are often multi-party. As part of Honda Research Institute’s Haru project a light weight word spotting speech recognition system - A conversational listener - was implemented to allow very fast turn-taking in simple voice interaction conditions. In this paper, we present a pilot evaluation of the conversational listener in a script follower context (which allows a robot to act out a dialog with a user). We compare a disembodied version of the system with expressive synthesis to Alexa with and without fast turn-taking. Qualitative results indicate that users were sensitive to turn-taking delay and characterful speech synthesis.

AB - Current spoken conversational user interfaces (CUIs) are predominantly implemented using a sequential, utterance based, two-party, speak-wait/speak-wait approach. Human-human conversation 1) is not sequential, with overlap, interruption and back channels; 2) processes utterances before they are complete and 3) are often multi-party. As part of Honda Research Institute’s Haru project a light weight word spotting speech recognition system - A conversational listener - was implemented to allow very fast turn-taking in simple voice interaction conditions. In this paper, we present a pilot evaluation of the conversational listener in a script follower context (which allows a robot to act out a dialog with a user). We compare a disembodied version of the system with expressive synthesis to Alexa with and without fast turn-taking. Qualitative results indicate that users were sensitive to turn-taking delay and characterful speech synthesis.

KW - conversational turn-taking

KW - evaluation

KW - human-machine voice interaction

KW - social robots

UR - http://www.scopus.com/inward/record.url?scp=85167818250&partnerID=8YFLogxK

U2 - 10.1145/3571884.3605871

DO - 10.1145/3571884.3605871

M3 - Conference contribution

SN - 9798400700149

BT - CUI '23: Proceedings of the 5th International Conference on Conversational User Interfaces

PB - Association for Computing Machinery

T2 - 5th International Conference on Conversational User Interfaces 2023

Y2 - 19 July 2023 through 21 July 2023

ER -

A Pilot Evaluation of a Conversational Listener for Conversational User Interfaces

Abstract

Conference

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this