Respiratory Turn-Taking Cues

Włodarczak, Marcin; Heldner, Mattias

doi:10.21437/interspeech.2016-346

Cited by 14 publications

(17 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…By contrast, [2] found that inhalation tends to be deeper in turn-holding than in turn-changing pauses, although the size of this effect seemed to be rather small. By including an additional category of backchannel-like utterances in our own work we have been able to identify consistent variation in inhalation amplitude across turn-categories [3]. We also found that relatively increased lung volume at the inhalation onset cued speech inhalations, which we hypothesized to be a strategy for arriving at timely speaker transition.…”

Section: Introductionsupporting

confidence: 52%

“…When fBL (·) is implemented as a Jelinek-Mercer-smoothed n-gram model as described in [15], the cross-entropies for TRAINSET and TESTSET are 0.256 bits/100ms and 0.239 bits/100ms, respectively; these are shown as baseline "1" in Figure 2. Baseline "2" represents an NN-based MI implementation [6] as described in Subsection 2.3; as for all other NNs in this article, we used J = 32 hidden units (decided using TRAINSET), with one hundred iterations of scaled conjugate gradient (SCG) pre-training 3 and one thousand iterations of SCG training. The performance of baselines "1" and "2" differs only negligibly 4 .…”

Section: Baseline Developmentmentioning

confidence: 99%

“…In particular, several studies [1,2,3] have identified temporal compression, whereby the lag preceding and following the inhalation as well as the duration of the inhalation itself are reduced, a practice interpreted as a strategy to minimize the likelihood of pause interruption. In addition, exhalations were shown to be longer before speaker changes than before turn continuations [4], and preparing to take the turn was associated with an increased inhalation amplitude compared to the silent breathing pattern [2].…”

Section: Introductionmentioning

confidence: 99%

“…The resulting study is therefore an important extension of our earlier work on respiratory turn-taking cues [3]. In that work, we had modeled each conversation partner individually, without taking their interlocutors' behavior into consideration.…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Improving Prediction of Speech Activity Using Multi-Participant Respiratory State

Włodarczak¹,

Laskowski²,

Heldner³

et al. 2017

Interspeech 2017

Self Cite

View full text Add to dashboard Cite

One consequence of situated face-to-face conversation is the coobservability of participants' respiratory movements and sounds. We explore whether this information can be exploited in predicting incipient speech activity. Using a methodology called stochastic turn-taking modeling, we compare the performance of a model trained on speech activity alone to one additionally trained on static and dynamic lung volume features. The methodology permits automatic discovery of temporal dependencies across participants and feature types. Our experiments show that respiratory information substantially lowers cross-entropy rates, and that this generalizes to unseen data.

show abstract

Section: Introductionsupporting

confidence: 52%

Section: Baseline Developmentmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Improving Prediction of Speech Activity Using Multi-Participant Respiratory State

Włodarczak¹,

Laskowski²,

Heldner³

et al. 2017

Interspeech 2017

Self Cite

View full text Add to dashboard Cite

show abstract

“…Given that REL is heavily influence by posture shifts, it was estimated following a procedure we proposed in Włodarczak and Heldner (2016b). Specifically, REL was taken as the mean level of troughs in the previous 20 respiratory cycles.…”

Section: Methodsmentioning

confidence: 99%

Respiratory Constraints in Verbal and Non-verbal Communication

Włodarczak

Heldner

2017

Front. Psychol.

Self Cite

View full text Add to dashboard Cite

In the present paper we address the old question of respiratory planning in speech production. We recast the problem in terms of speakers' communicative goals and propose that speakers try to minimize respiratory effort in line with the H&H theory. We analyze respiratory cycles coinciding with no speech (i.e., silence), short verbal feedback expressions (SFE's) as well as longer vocalizations in terms of parameters of the respiratory cycle and find little evidence for respiratory planning in feedback production. We also investigate timing of speech and SFEs in the exhalation and contrast it with nods. We find that while speech is strongly tied to the exhalation onset, SFEs are distributed much more uniformly throughout the exhalation and are often produced on residual air. Given that nods, which do not have any respiratory constraints, tend to be more frequent toward the end of an exhalation, we propose a mechanism whereby respiratory patterns are determined by the trade-off between speakers' communicative goals and respiratory constraints.

show abstract