Gtr-voice: Articulatory Phonetics Informed Controllable Expressive Speech Synthesis

Abstract

Expressive speech synthesis aims to generate speech that captures a wide range of para-linguistic features, including emotion and articulation, though current research primarily emphasizes emotional aspects over the nuanced articulatory features mastered by professional voice actors. Inspired by this, we explore expressive speech synthesis through the lens of articulatory phonetics. Specifically, we define a framework with three dimensions: Glottalization, Tenseness, and Resonance (GTR), to guide the synthesis at the voice production level. With this framework, we record a high-quality speech dataset named GTR-Voice, featuring 20 Chinese sentences articulated by a professional voice actor across 125 distinct GTR combinations. We verify the framework and GTR annotations through automatic classification and listening tests, and demonstrate precise controllability along the GTR dimensions on two fine-tuned expressive TTS models. We open-source the dataset and TTS models.

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keyli2024gtr

Related papers

• A Methodology For Controlling The Emotional Expressiveness In Synthetic Speech -- A Deep Learning Approach (2019)5.84
• Storytts: A Highly Expressive Text-to-speech Dataset With Rich Textual Expressiveness Annotations (2024)3.58
• Time Out Of Mind: Generating Rate Of Speech Conditioned On Emotion And Speaker (2023)0.00
• PROEMO: Prompt-driven Text-to-speech Synthesis Based On Emotion And Intensity Control (2025)0.00
• Facespeak: Expressive And High-quality Speech Synthesis From Human Portraits Of Different Styles (2025)0.00
• Towards Controllable Speech Synthesis In The Era Of Large Language Models: A Systematic Survey (2024)4.75
• EE-TTS: Emphatic Expressive TTS With Linguistic Information (2023)2.26
• Textrolspeech: A Text Style Control Speech Corpus With Codec Language Text-to-speech Models (2023)9.59