Gespeichert in:
| Hauptverfasser: | , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | https://arxiv.org/abs/2406.10514 |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866909228629753856 |
|---|---|
| author | Li, Zehua Kcriss Chen, Meiying Melissa Zhong, Yi Liu, Pinxin Duan, Zhiyao |
| author_facet | Li, Zehua Kcriss Chen, Meiying Melissa Zhong, Yi Liu, Pinxin Duan, Zhiyao |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2406_10514 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | GTR-Voice: Articulatory Phonetics Informed Controllable Expressive Speech Synthesis Li, Zehua Kcriss Chen, Meiying Melissa Zhong, Yi Liu, Pinxin Duan, Zhiyao Audio and Speech Processing Artificial Intelligence Computation and Language Machine Learning Sound 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. |
| title | GTR-Voice: Articulatory Phonetics Informed Controllable Expressive Speech Synthesis |
| topic | Audio and Speech Processing Artificial Intelligence Computation and Language Machine Learning Sound |
| url | https://arxiv.org/abs/2406.10514 |