Research map / Label-efficient and robust learning / Zero-/few-shot and meta-learning
GenerSpeech: Towards Style Transfer for Generalizable Out-Of-Domain Text-to-Speech
Rongjie Huang, Yi Ren, Jinglin Liu, Chenye Cui, Zhou Zhao
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| Use GenerSpeech instead of FG-TransformerTTS | OOD style transfer · VCTK, parallel | MOS: 3.95 ± 0.1 -> 4.06 ± 0.08 | Improved |
| Use GenerSpeech instead of Meta-StyleSpeech | OOD style transfer · VCTK, parallel | SMOS: 3.95 ± 0.08 -> 4.01 ± 0.09 | Improved |
| Use GenerSpeech instead of FG-TransformerTTS | OOD style transfer · VCTK, parallel | Cos: 0.86 -> 0.88 | Improved |
| Use GenerSpeech instead of FG-TransformerTTS | OOD style transfer · VCTK, parallel | FFE: 0.30 -> 0.35 | Hurt |
| Use GenerSpeech instead of Expressive FS2 | OOD style transfer · ESD, parallel | MOS: 4.04 ± 0.08 -> 4.11 ± 0.10 | Improved |
| Use GenerSpeech instead of Styler | OOD style transfer · ESD, parallel | SMOS: 4.05 ± 0.08 -> 4.20 ± 0.09 | Improved |
| Use GenerSpeech instead of Expressive FS2 | OOD style transfer · ESD, parallel | Cos: 0.93 -> 0.97 | Improved |
| Use GenerSpeech instead of Mellotron | OOD style transfer · ESD, parallel | FFE: 0.27 -> 0.26 | Improved |
| Add the multi-level local style encoder (ablation) | GenerSpeech · Ablation evaluation | CMOS: 0.0 vs -0.02 | Improved |
| Add the multi-level local style encoder (ablation) | GenerSpeech · Ablation evaluation | CSMOS: 0.0 vs -0.15 | Improved |
| Use Mix-Style layer normalization instead of original layer normalization (ablation) | GenerSpeech · Ablation evaluation | CMOS: 0.0 vs -0.06 | Improved |
| Use Mix-Style layer normalization instead of original layer normalization (ablation) | GenerSpeech · Ablation evaluation | CSMOS: 0.0 vs -0.07 | Improved |
Later papers that compared with this method
1 later accepted paper reports GenerSpeech as a baseline in their results tables; 1 of them report a better number on most of the results they share with it.
- StyleSinger: Style Transfer for Out-of-Domain Singing Voice Synthesis (AAAI 2024 · better on 4 of 4 shared results)
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- StyleSinger: Style Transfer for Out-of-Domain Singing Voice Synthesis (AAAI 2024 · similarity 0.91)
- MM-TTS: Multi-Modal Prompt Based Style Transfer for Expressive Text-to-Speech Synthesis (AAAI 2024 · similarity 0.89)
- StableVC: Style Controllable Zero-Shot Voice Conversion with Conditional Flow Matching (AAAI 2025 · similarity 0.88)
- Vevo: Controllable Zero-Shot Voice Imitation with Self-Supervised Disentanglement (ICLR 2025 · similarity 0.88)
- Mega-TTS 2: Boosting Prompting Mechanisms for Zero-Shot Speech Synthesis (ICLR 2024 · similarity 0.86)
- NaturalSpeech 2: Latent Diffusion Models are Natural and Zero-Shot Speech and Singing Synthesizers (ICLR 2024 · similarity 0.86)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
