Saved in:
Bibliographic Details
Main Authors: Qian, Livia, Figueroa, Carol, Skantze, Gabriel
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2505.13268
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908370625101824
author Qian, Livia
Figueroa, Carol
Skantze, Gabriel
author_facet Qian, Livia
Figueroa, Carol
Skantze, Gabriel
contents Vocal feedback (e.g., `mhm', `yeah', `okay') is an important component of spoken dialogue and is crucial to ensuring common ground in conversational systems. The exact meaning of such feedback is conveyed through both lexical and prosodic form. In this work, we investigate the perceived prosodic similarity of vocal feedback with the same lexical form, and to what extent existing speech representations reflect such similarities. A triadic comparison task with recruited participants is used to measure perceived similarity of feedback responses taken from two different datasets. We find that spectral and self-supervised speech representations encode prosody better than extracted pitch features, especially in the case of feedback from the same speaker. We also find that it is possible to further condense and align the representations to human perception through contrastive learning.
format Preprint
id arxiv_https___arxiv_org_abs_2505_13268
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Representation of perceived prosodic similarity of conversational feedback
Qian, Livia
Figueroa, Carol
Skantze, Gabriel
Computation and Language
Artificial Intelligence
Machine Learning
Vocal feedback (e.g., `mhm', `yeah', `okay') is an important component of spoken dialogue and is crucial to ensuring common ground in conversational systems. The exact meaning of such feedback is conveyed through both lexical and prosodic form. In this work, we investigate the perceived prosodic similarity of vocal feedback with the same lexical form, and to what extent existing speech representations reflect such similarities. A triadic comparison task with recruited participants is used to measure perceived similarity of feedback responses taken from two different datasets. We find that spectral and self-supervised speech representations encode prosody better than extracted pitch features, especially in the case of feedback from the same speaker. We also find that it is possible to further condense and align the representations to human perception through contrastive learning.
title Representation of perceived prosodic similarity of conversational feedback
topic Computation and Language
Artificial Intelligence
Machine Learning
url https://arxiv.org/abs/2505.13268