Towards Interactive Annotation for Hesitation in Conversational Speech - Archive ouverte HAL Access content directly
Conference Papers Year : 2020

Towards Interactive Annotation for Hesitation in Conversational Speech

Abstract

Manual annotation of speech corpora is costly in both human resources and time. Furthermore, recognizing affects in spontaneous, non acted speech presents a challenge for humans and machines. The aim of the present study is to automatize the labeling of hesitant speech as a marker of expressed uncertainty. That is why, the NCCFr-corpus was manually annotated for on a continuous scale between-3 and 3 and the affective dimensions ,. In total, 5834 chunks of the NCCFr-corpus were manually annotated. Acoustic analyses were carried out based on these annotations. Furthermore, regression models were trained in order to allow automatic prediction of hesitation for speech chunks that do not have a manual annotation. Preliminary results show that the number of filled pauses as well as vowel duration increase with the degree of hesitation, and that automatic prediction of the hesitation degree reaches encouraging RMSE results of 1.6.
Fichier principal
Vignette du fichier
LREC_2020___NCCFR(2).pdf (437.57 Ko) Télécharger le fichier
Origin : Files produced by the author(s)
Loading...

Dates and versions

hal-02505333 , version 1 (11-03-2020)

Identifiers

  • HAL Id : hal-02505333 , version 1

Cite

Jane Wottawa, Marie Tahon, Apolline Marin, Nicolas Audibert. Towards Interactive Annotation for Hesitation in Conversational Speech. LREC 2020, May 2020, Marseille, France. ⟨hal-02505333⟩
241 View
121 Download

Share

Gmail Facebook X LinkedIn More