Contrast in concept-to-speech generation

Theune, Mariët

doi:10.1016/s0885-2308(02)00010-4

Cited by 10 publications

(3 citation statements)

References 81 publications

(87 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…As regards our work on intonation, as stated in the introduction, Prevost's (1995) generator has directly informed our approach to information structure and prosody; his system does not make use of quantitative user models though, and only describes single options. Theune (2002) likewise follows Prevost's approach in her system, refining the way contrast is determined in assigning pitch accents. Theune et al (2001) show that a system employing syntactic templates and a rule-based prosody assignment algorithm leads to more natural synthesis (of Dutch); unlike FLIGHTS though, their D2S system does not employ a user preference model or a notion of theme phrase, and does not distinguish different types of pitch accents.…”

Section: Related Workmentioning

confidence: 95%

Generating Tailored, Comparative Descriptions with Contextually Appropriate Intonation

White¹,

Clark²,

Moore³

2010

Computational Linguistics

View full text Add to dashboard Cite

Generating responses that take user preferences into account requires adaptation at all levels of the generation process. This article describes a multi-level approach to presenting user-tailored information in spoken dialogues which brings together for the first time multi-attribute decision models, strategic content planning, surface realization that incorporates prosody prediction, and unit selection synthesis that takes the resulting prosodic structure into account. The system selects the most important options to mention and the attributes that are most relevant to choosing between them, based on the user model. Multiple options are selected when each offers a compelling trade-off. To convey these trade-offs, the system employs a novel presentation strategy which straightforwardly lends itself to the determination of information structure, as well as the contents of referring expressions. During surface realization, the prosodic structure is derived from the information structure using Combinatory Categorial Grammar in a way that allows phrase boundaries to be determined in a flexible, data-driven fashion. This approach to choosing pitch accents and edge tones is shown to yield prosodic structures with significantly higher acceptability than baseline prosody prediction models in an expert evaluation. These prosodic structures are then shown to enable perceptibly more natural synthesis using a unit selection voice that aims to produce the target tunes, in comparison to two baseline synthetic voices. An expert evaluation and f0 analysis confirm the superiority of the generator-driven intonation and its contribution to listeners' ratings.

show abstract

Section: Related Workmentioning

confidence: 95%

Generating Tailored, Comparative Descriptions with Contextually Appropriate Intonation

White¹,

Clark²,

Moore³

2010

Computational Linguistics

View full text Add to dashboard Cite

show abstract

“…Since human speakers use deictic gestures and other nonverbal signals mainly to convey new information, another condition is that the object should be new, i.e., not previously mentioned, inferable, or otherwise familiar to the user. We also assume that deictic signals are appropriate for objects that are mentioned in a contrastive context (for ways to detect contrast using a discourse model, see Prevost, 1995, Theune, 2002. In short, first or contrastive references to visible objects will be accompanied by a deictic nonverbal signal.…”

Section: Deictic Signals and The Generation Of Referring Expressionsmentioning

confidence: 99%

Generating Embodied Information Presentations

Theune

Heylen

Nijholt

2005

Multimodal Intelligent Information Presentation

View full text Add to dashboard Cite

Abstract. The output modalities available for information presentation by embodied, human-like agents include both language and various nonverbal cues such as pointing and gesturing. These human, nonverbal modalities can be used to emphasize, extend or even replace the language output produced by the agent. To deal with the interdependence between language and nonverbal signals, their production processes should be integrated. In this chapter, we discuss the issues involved in extending a natural language generation system with the generation of nonverbal signals. We sketch a general architecture for embodied language generation, discussing the interaction between the production of nonverbal signals and language generation, and the different factors influencing the choice between the available modalities. As an example we describe the generation of route descriptions by an embodied agent in a 3D environment.

show abstract

“…These coherent structures have benefit various NLP applications such as text summarization [7][8] [9][10] [11] [12], question answering [13] [14] and natural language generation [15] [16]. For instance, Litkowski proposed an approach that makes use of structural information of sentences, such as the discourse entities and semantic relation to generate database for question answering system [13].…”

Section: Introductionmentioning

confidence: 99%