Automatic User-Adaptive Speaking Rate Selection

Ward, Nigel; Nakagawa, Satoshi

doi:10.1023/b:ijst.0000037070.31146.f9

Cited by 17 publications

(13 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Users' amicability for a machine increases when it adapts to their prosody (Suzuki and Katagiri, 2007). Ward and Nakagawa (2002) found for instance that a telephony system that adapts its speech rate with the users' is rated more favourably than those that do not.…”

Section: Functional Role In Social Interactionmentioning

confidence: 99%

“…These language technologies have use in a diverse range of fields including mobile communications (Ward and Nakagawa, 2002;Lu et al, 2011;Agarwal et al, 2011) internet search engines (Google, 2011;Apple Inc, 2011), games and assistive technologies developed for the elderly (Kleinberger et al, 2007) or communicatively impaired (Zhou et al, 2012). While these interactive systems can process the linguistic aspects of human communication, they are not yet capable of processing the important suprasegmental social information that is a pervasive part of human social interaction.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Investigating automatic measurements of prosodic accommodation and its dynamics in social interaction

Looze

Scherer

Vaughan

et al. 2014

Speech Communication

101

View full text Add to dashboard Cite

Spoken dialogue systems are increasingly being used to facilitate and enhance human communication. While these interactive systems can process the linguistic aspects of human communication, they are not yet capable of processing the complex dynamics involved in social interaction, such as the adaptation on the part of interlocutors. Providing interactive systems with the capacity to process and exhibit this accommodation could however improve their efficiency and make machines more socially-competent interactants.At present, no automatic system is available to process prosodic accommodation, nor do any clear measures exist that quantify its dynamic manifestation. While it can be observed to be a monotonically manifest property, it is our hypotheses that it evolves dynamically with functional social aspects.In this paper, we propose an automatic system for its measurement and the capture of its dynamic manifestation. We investigate the evolution of prosodic accommodation in 41 Japanese dyadic telephone conversations and discuss its manifestation in relation to its functions in social interaction. Overall, our study shows that prosodic accommodation changes dynamically over the course of a conversation and across conversations, and that these dynamics inform about the naturalness of the conversation flow, the speakers' degree of involvement and their affinity in the conversation.

show abstract

Section: Functional Role In Social Interactionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Investigating automatic measurements of prosodic accommodation and its dynamics in social interaction

Looze

Scherer

Vaughan

et al. 2014

Speech Communication

101

View full text Add to dashboard Cite

show abstract

“…When people engage in conversation, they tailor their utterances to their conversational partners, whether these partners are other humans or computational systems (Brennan, 1991;Schober, 1998). This tailoring, or adaptation to the partner, has been shown to take place in all facets of human language use, including speaking rate and response delay Ward & Nakagawa, 2002), amplitude and prosodic range (Coulston, Oviatt, & Darves, 2002;McLemore, 1992), lexical and syntactic choice (Brennan, 1996;Kempen & Hoenkamp, 1987;Levelt & Kelter, 1982), choice and modality of referring expressions (Bell, Boye, Gustafson, & Wirn, 2000;Brennan & Clark, 1996;Garrod & Anderson, 1987;Schober, 1998) and in higher level discourse processes such as the selection of content and form for persuasive arguments and negotiation (Joshi, 1982;Joshi, Webber, & Weischedel, 1984;Mayberry & Golden, 1996;McGuire, 1968;Walker, 1996;Webber & Joshi, 1982). This adaptive behavior is based on a mental model or a user model of the conversational partner (Brennan & Clark, 1996;Levelt, 1989;Wahlster & Kobsa, 1989;Zukerman & Litman, 2001).…”

Section: Introductionmentioning

confidence: 99%

Generation and evaluation of user tailored responses in multimodal dialogue

et al. 2004

View full text Add to dashboard Cite

When people engage in conversation, they tailor their utterances to their conversational partners, whether these partners are other humans or computational systems. This tailoring, or adaptation to the partner takes place in all facets of human language use, and is based on a mental model or a user model of the conversational partner. Such adaptation has been shown to improve listeners' comprehension, their satisfaction with an interactive system, the efficiency with which they execute conversational tasks, and the likelihood of achieving higher level goals such as changing the listener's beliefs and attitudes. We focus on one aspect of adaptation, namely the tailoring of the content of dialogue system utterances for the higher level processes of persuasion, argumentation and advice-giving. Our hypothesis is that algorithms that adapt content for these processes, according to a user model, will improve the usability, efficiency, and effectiveness of dialogue systems. We describe a multimodal dialogue system and algorithms for adaptive content selection based on multi-attribute decision theory. We demonstrate experimentally the improved efficacy of system responses through the use of user models to both tailor the content of system utterances and to manipulate their conciseness.

show abstract

“…To reproduce an interaction with speech rate similarity, studies have focused on mechanisms to measure user speech rates (Takamaru, Hiroshige, Araki & Tochinai 2000) and to pace synthesized voices to match user speech rates (Iwase & Ward 1998;Ward & Nakagawa 2002). Another study argues that task structure rather than the partner's speech rate is the dominant factor in human conversation and determines the speaking rate (Ward & Mamidipally 2008).…”

Section: B Related Research In Spoken Dialogsmentioning

confidence: 99%

What is the appropriate speech rate for a communication robot?

Shimada¹,

Kanda²

2012

inter stud

View full text Add to dashboard Cite

This study investigates the influence of a robot's speech rate. In human communication, slow speech is considered boring, speech at normal speed is perceived as credible, and fast speech is perceived as competent. To seek the appropriate speech rate for robots, we test whether these tendencies are replicated in human-robot interaction by conducting an experiment with four rates of speech: fast, normal, moderately slow, and slow. Our experimental results reveal a rather surprising trend. Participants prefer normal and moderately slow speech to fast speech. A robot that provides normal or moderately slow speech is perceived as competent. We further study how context affects this perception. In a situation where the robot and participants talk while walking, we found that slow speech was the most comprehensible. In addition, slow speech is subjectively perceived as good as moderately slow and normal speech.

show abstract

Automatic User-Adaptive Speaking Rate Selection

Cited by 17 publications

References 21 publications

Investigating automatic measurements of prosodic accommodation and its dynamics in social interaction

Investigating automatic measurements of prosodic accommodation and its dynamics in social interaction

Generation and evaluation of user tailored responses in multimodal dialogue

What is the appropriate speech rate for a communication robot?

Contact Info

Product

Resources

About