Communication Dans Un Congrès Année : 2024

Mhm... Yeah? Okay! Evaluating the Naturalness and Communicative Function of Synthesized Feedback Responses in Spoken Dialogue

Résumé

To create conversational systems with humanlike listener behavior, generating short feedback responses (e.g., "mhm", "ah", "wow") appropriate for their context is crucial. These responses convey their communicative function through their lexical form and their prosodic realization. In this paper, we transplant the prosody of feedback responses from humanhuman U.S. English telephone conversations to a target speaker using two synthesis techniques (TTS and signal processing). Our evaluation focuses on perceived naturalness, contextual appropriateness and preservation of communicative function. Results indicate TTS-generated feedback were perceived as more natural than signal-processing-based feedback, with no significant difference in appropriateness. However, the TTS did not consistently convey the communicative function of the original feedback.

Fichier principal
Vignette du fichier
2024.sigdial-1.46.pdf (863.06 Ko) Télécharger le fichier
Origine Fichiers produits par l'(les) auteur(s)
Licence

Dates et versions

hal-04722303 , version 1 (04-10-2024)

Licence

Identifiants

  • HAL Id : hal-04722303 , version 1

Citer

Carol Figueroa, Marcel de Korte, Magalie Ochs, Gabriel Skantze. Mhm... Yeah? Okay! Evaluating the Naturalness and Communicative Function of Synthesized Feedback Responses in Spoken Dialogue. Proceedings of the 25th Annual Meeting of the Special Interest Group on Discourse and Dialogue, Sep 2024, Kyoto, Japan. ⟨hal-04722303⟩
177 Consultations
256 Téléchargements

Partager

  • More