Direct Scaling of Perceptual Dimensions in a Conversational Situation

Köster, Friedemann

doi:10.1007/978-981-10-5224-8_5

Cited by 1 publication

(5 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This leads to an interaction between both participants that is described as a four-state model in [12]: One participant can either speak or listen, as in addition both participants can also speak or remain silent at the same time. From a speechquality point-of-view, this leads to a separation of a conversation into three phases as perceived by one participant: The Lis- Table 1: Overview of the three phases and their seven perceptual quality dimensions for a conversational situation [9,10,11].…”

Section: Phases In a Conversational Situationmentioning

confidence: 99%

“…This sums up to seven perceptual dimensions grouped into three phases of a conversation. This quality profile was validated in [11], and an overview of the three phases and their perceptual dimensions can be seen in Table 1.…”

Section: Phases In a Conversational Situationmentioning

confidence: 99%

“…In [11] the demand for a test paradigm that allows the participants to perceive each phase of a conversation separately was discussed. The new test paradigm, its design according to [14], and the setup are introduced in the following.…”

Section: Conversational Experimentsmentioning

confidence: 99%

“…LPC-10), using open-source implementations. The same setup was used for the experiments discussed in [10] and [11].…”

Section: Technical Setupmentioning

confidence: 99%

“…In separate listening, speaking and interaction experiments seven perceptual dimensions were identified for a conversational situation: four for the Listening Phase [9], two for the Speaking Phase, and one for the Interaction Phase [10]. The seven dimensions were validated in a complete conversation test [11]. The direct scaling of all dimensions requires a new test paradigm which allows the participants to perceive each conversational phase separately.…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

Analyzing the Relation Between Overall Quality and the Quality of Individual Phases in a Telephone Conversation

Köster

Möller

2016

Interspeech 2016

Self Cite

View full text Add to dashboard Cite

Assessing and analyzing the quality of transmitted speech in a conversational situation is an important topic in current research. For this, a conversation has been separated into three individual conversational phases (listening, speaking, and interaction), and for each phase corresponding quality-relevant perceptual dimensions have been identified. The dimensions can be used to determine the quality of each phase, and the qualities of all phases, in turn, can be be combined for overall conversational quality estimation. In this article we present the work that has been conducted to identify the weights of the individual phases for the overall quality. For this, we conducted an experiment that allows the participants to perceive each phase separately and to gather the overall quality as well as the quality ratings for each individual phase. The results enable to create a linear model to predict the overall quality on the basis of the three phases. This allows to draw first conclusions regarding the relation between the individual phases and the overall quality and provides a major landmark towards a diagnostic assessment of conversational quality.

show abstract

Section: Phases In a Conversational Situationmentioning

confidence: 99%

Section: Phases In a Conversational Situationmentioning

confidence: 99%

Section: Conversational Experimentsmentioning

confidence: 99%

“…LPC-10), using open-source implementations. The same setup was used for the experiments discussed in [10] and [11].…”

Section: Technical Setupmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%