Analysis of Changes in Dialogue Rhythm Due to Dialogue Acts in Task-Oriented Dialogues

Fujiwara, Noriki; Itoh, Takuzì; Araki, Kenji

doi:10.1007/978-3-540-74628-7_73

Cited by 7 publications

(6 citation statements)

References 5 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Between the fine-grained phone and the coarser word and utterance levels, syllabic segmentation provides insight both in the phonological and rhythmic aspects of speech. It can be put to use in various applications, for example in analysing dialogue for humanmachine interaction [1]. The identification of the vowel constituting the core of a syllable, the syllable nucleus, is a key part in measuring speech prominence [2], and speech recognition has been helped by information about the syllabic structure of utterances [3], such as the number of syllables in an utterance or the position of syllable nuclei.…”

Section: Introductionmentioning

confidence: 99%

Syllabification of conversational speech using Bidirectional Long-Short-Term Memory Neural Networks

Landsiedel

Edlund

Eyben

et al. 2011

2011 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

View full text Add to dashboard Cite

Segmentation of speech signals is a crucial task in many types of speech analysis. We present a novel approach at segmentation on a syllable level, using a Bidirectional Long-Short-Term Memory Neural Network. It performs estimation of syllable nucleus positions based on regression of perceptually motivated input features to a smooth target function. Peak selection is performed to attain valid nuclei positions. Performance of the model is evaluated on the levels of both syllables and the vowel segments making up the syllable nuclei. The general applicability of the approach is illustrated by good results for two common databases-Switchboard and TIMIT-for both read and spontaneous speech, and a favourable comparison with other published results.

show abstract

Section: Introductionmentioning

confidence: 99%

Syllabification of conversational speech using Bidirectional Long-Short-Term Memory Neural Networks

Landsiedel

Edlund

Eyben

et al. 2011

2011 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

View full text Add to dashboard Cite

show abstract

“…There are a vast number of potential applications, including driver identification [23], driver distraction detection [24]- [26], emotion and stress detection/estimation [27], [28], mining potentially hazardous situations [29], and route recognition [27]. In this section, we present three sample applications in the areas of driver distraction/cognitive load, frustration estimation, and lane tracking.…”

Section: Sample Applicationsmentioning

confidence: 99%

International Large-Scale Vehicle Corpora for Research on Driver Behavior on the Road

Takeda

Hansen

Boyraz

et al. 2011

IEEE Trans. Intell. Transport. Syst.

View full text Add to dashboard Cite

This paper considers a comprehensive and collaborative project to collect large amounts of driving data on the road for use in a wide range of areas of vehicle-related research centered on driving behavior. Unlike previous data collection efforts, the corpora collected here contain both human and vehicle sensor data, together with rich and continuous transcriptions. While most efforts on in-vehicle research are generally focused within individual countries, this effort links a collaborative team from three diverse regions (i.e., Asia, American, and Europe). Details relating to the data collection paradigm, such as sensors, driver information, routes, and transcription protocols, are discussed, and a preliminary analysis of the data across the three data collection sites from the U.S. (Dallas), Japan (Nagoya), and Turkey (Istanbul) is provided. The usability of the corpora has been experimentally verified with a Cohen's kappa coefficient of 0.74 for transcription reliability, as well as being successfully exploited for several in-vehicle applications. Most importantly, the corpora are publicly available for research use and represent one of the first multination efforts to share resources and understand driver characteristics. Future work on distributing the corpora to the wider research community is also discussed.

show abstract

“…We first consider the reason why agreement-Reaction occurred at early timing, based on the discussion by Fujiwara et al [4]. If the respondent reacts at late timing, his partner may imagine that he is not sure which is better.…”

Section: Discussion -What Does the Face-turning Action Imply In Consementioning

confidence: 99%

“…Some researchers have argued that the respondent unconsciously controls the timing structure I UU as the negative response timing is later than the positive one in the task-oriented dialogue [4]. The respondent would also control the timing of utterance, I UU , according to agreement/disagreement with the partner.…”

Section: Relations Between the Timing Structures And The Respondent'smentioning

confidence: 99%

See 1 more Smart Citation

What Does the Face-Turning Action Imply in Consensus Building Communication?

Onishi

Hirayama

Matsuyama

Machine Learning for Multimodal Interaction

View full text Add to dashboard Cite

Abstract. When talking with someone, we convey intention to each other by verbal and non-verbal behaviors. In consensus building dialogue, the participants need to understand whether they agree or disagree. They reiterate confirmation of partner's internal state (agreement/disagreement) and reaction for it. In this study, we considered that the timing of listener's reaction for the confirmation by a speaker reflects listener's internal state, therefore analyzed the multimodal timing structures between the confirmation and the reaction by utterance and body motion. Especially, we focused on an action that the speaker turns his face toward the listener as the confirming action and analyzed how it influences the timing structures. As the results, we confirmed that the timing structures relate to the internal state and the relations are controlled by face-turning action.

show abstract

Analysis of Changes in Dialogue Rhythm Due to Dialogue Acts in Task-Oriented Dialogues

Cited by 7 publications

References 5 publications

Syllabification of conversational speech using Bidirectional Long-Short-Term Memory Neural Networks

Syllabification of conversational speech using Bidirectional Long-Short-Term Memory Neural Networks

International Large-Scale Vehicle Corpora for Research on Driver Behavior on the Road

What Does the Face-Turning Action Imply in Consensus Building Communication?

Contact Info

Product

Resources

About