# Voice Quality Dimensions as Interpretable Primitives for Speaking Style for Atypical Speech and Affect

arXiv: https://arxiv.org/abs/2505.21809 · HTML: https://mlsanity.com/paper/2505.21809/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 11 of its 34 references that are in the map.
- First posted on arXiv 27 May 2025.

## Builds on (most cited first, 11 of 11)

- [HuBERT: Self-Supervised Speech Representation Learning by Masked Prediction of Hidden Units](https://mlsanity.com/paper/2106.07447/) (2021)
- [AVEC 2019 Workshop and Challenge: State-of-Mind, Detecting Depression with AI, and Cross-Cultural Affect Recognition](https://mlsanity.com/paper/1907.11510/) (2019)
- [On the Utility of Self-supervised Models for Prosody-related Tasks](https://mlsanity.com/paper/2210.07185/) (2022)
- [Universal Paralinguistic Speech Representations Using Self-Supervised Conformers](https://mlsanity.com/paper/2110.04621/) (2021)
- [ESPnet-SPK: full pipeline speaker embedding toolkit with reproducible recipes, self-supervised front-ends, and off-the-shelf models](https://mlsanity.com/paper/2401.17230/) (2024)
- [EasyCall corpus: a dysarthric speech dataset](https://mlsanity.com/paper/2104.02542/) (2021)
- [Investigating the Emergent Audio Classification Ability of ASR Foundation Models](https://mlsanity.com/paper/2311.09363/) (2023)
- [Investigating salient representations and label Variance in Dimensional Speech Emotion Analysis](https://mlsanity.com/paper/2312.16180/) (2023)
- [Seq2seq for Automatic Paraphasia Detection in Aphasic Speech](https://mlsanity.com/paper/2312.10518/) (2023)
- [Speech Intelligibility Classifiers from 550k Disordered Speech Samples](https://mlsanity.com/paper/2303.07533/) (2023)
- [Objective Measurements of Voice Quality](https://mlsanity.com/paper/2410.09578/) (2024)

## Built on by (most cited first, 1 of 1)

- [Something from Nothing: Data Augmentation for Robust Severity Level Estimation of Dysarthric Speech](https://mlsanity.com/paper/2603.15988/) (2026)

## Abstract (arXiv)

Perceptual voice quality dimensions describe key characteristics of atypical speech and other speech modulations. Here we develop and evaluate voice quality models for seven voice and speech dimensions (intelligibility, imprecise consonants, harsh voice, naturalness, monoloudness, monopitch, and breathiness). Probes were trained on the public Speech Accessibility (SAP) project dataset with 11,184 samples from 434 speakers, using embeddings from frozen pre-trained models as features. We found that our probes had both strong performance and strong generalization across speech elicitation categories in the SAP dataset. We further validated zero-shot performance on additional datasets, encompassing unseen languages and tasks: Italian atypical speech, English atypical speech, and affective speech. The strong zero-shot performance and the interpretability of results across an array of evaluations suggests the utility of using voice quality dimensions in speaking style-related tasks.