Synthesizing speech with selected perceptual voice qualities - A case study with creaky voice

2025/11/07 by Rautenberg, Frederik, Seebauer, Fritz, Wiechmann, Jana +3
#Audio and Speech Processing (eess.AS) #FOS: Electrical engineering #electronic engineering #information engineering

paper · doi:10.48550/arxiv.2511.05143

Abstract

The control of perceptual voice qualities in a text-to-speech (TTS) system is of interest for applications where unmanipu- lated and manipulated speech probes can serve to illustrate pho- netic concepts that are otherwise difficult to grasp. Here, we show that a TTS system, that is augmented with a global speaker attribute manipulation block based on normalizing flows1 , is capable of correctly manipulating the non-persistent, localized quality of creaky voice, thus avoiding the necessity of a, typi- cally unreliable, frame-wise creak predictor. Subjective listen- ing tests confirm successful creak manipulation at a slightly re- duced MOS score compared to the original recording.

Citations

• Speech Synthesis along Perceptual Voice Quality Dimensions
• GTR-Voice: Articulatory Phonetics Informed Controllable Expressive Speech Synthesis
• VoiceShop: A Unified Speech-to-Speech Framework for Identity-Preserving Zero-Shot Voice Editing
• PerMod: Perceptually Grounded Voice Modification with Latent Diffusion Models
• Frame-wise and overlap-robust speaker embeddings for meeting diarization
• LibriTTS-R: A Restored Multi-Speaker Text-to-Speech Corpus
• Cross-domain Neural Pitch and Periodicity Estimation
• Robust Speech Recognition via Large-Scale Weak Supervision
• FreeVC: Towards High-Quality Text-Free One-Shot Voice Conversion
• NaturalSpeech: End-to-End Text to Speech Synthesis with Human-Level Quality
• Conditional Variational Autoencoder with Adversarial Learning for\n End-to-End Text-to-Speech
• HiFi-GAN: Generative Adversarial Networks for Efficient and High Fidelity Speech Synthesis
• LibriTTS: A Corpus Derived from LibriSpeech for Text-to-Speech
• FFJORD: Free-form Continuous Dynamics for Scalable Reversible Generative Models
• Neural Ordinary Differential Equations

Related

• Speech Synthesis along Perceptual Voice Quality Dimensions
• Data-driven Detection and Analysis of the Patterns of Creaky Voice
• Prosodic Parameter Manipulation in TTS generated speech for Controlled Speech Generation
• DeepFry: Identifying Vocal Fry Using Deep Neural Networks
• TTSDS -- Text-to-Speech Distribution Score