# Speech Synthesis along Perceptual Voice Quality Dimensions

arXiv: https://arxiv.org/abs/2501.08791 · HTML: https://mlsanity.com/paper/2501.08791/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 15 Jan 2025.

## Built on by (most cited first, 4 of 4)

- [Voice Impression Control in Zero-Shot TTS](https://mlsanity.com/paper/2506.05688/) (2025)
- [Lost in Phonation: Voice Quality Variation as an Evaluation Dimension for Speech Foundation Models](https://mlsanity.com/paper/2510.25577/) (2025)
- [What Counts as Real? Speech Restoration and Voice Quality Conversion Pose New Challenges to Deepfake Detection](https://mlsanity.com/paper/2603.14033/) (2026)
- [ReaFlow-TTS: Realization-Conditioned Flow Matching for High-Quality and Controllable Speech Synthesis](https://mlsanity.com/paper/2609.28906/) (2026)

## Abstract (arXiv)

While expressive speech synthesis or voice conversion systems mainly focus on controlling or manipulating abstract prosodic characteristics of speech, such as emotion or accent, we here address the control of perceptual voice qualities (PVQs) recognized by phonetic experts, which are speech properties at a lower level of abstraction. The ability to manipulate PVQs can be a valuable tool for teaching speech pathologists in training or voice actors. In this paper, we integrate a Conditional Continuous-Normalizing-Flow-based method into a Text-to-Speech system to modify perceptual voice attributes on a continuous scale. Unlike previous approaches, our system avoids direct manipulation of acoustic correlates and instead learns from examples. We demonstrate the system's capability by manipulating four voice qualities: Roughness, breathiness, resonance and weight. Phonetic experts evaluated these modifications, both for seen and unseen speaker conditions. The results highlight both the system's strengths and areas for improvement.