Skip to Main content Skip to Navigation
Conference papers

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.
Complete list of metadatas

Cited literature [24 references]  Display  Hide  Download

https://hal.archives-ouvertes.fr/hal-02505333
Contributor : Jane Wottawa <>
Submitted on : Wednesday, March 11, 2020 - 2:16:33 PM
Last modification on : Friday, March 13, 2020 - 1:45:21 AM

File

LREC_2020___NCCFR(2).pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-02505333, version 1

Collections

Citation

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

Share

Metrics

Record views

21

Files downloads

36