Research map / Vision-language and multimodal / Human and embodied modeling
RWEN-TTS: Relation-Aware Word Encoding Network for Natural Text-to-Speech Synthesis
Shinhyeok Oh, HyeongRae Noh, Yoonseok Hong, Insoo Oh
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 |
|---|---|---|---|
| add SRE and AWRE relation encoding | FastPitch w/ UAL · LJSpeech | MOS: 4.16 -> 4.19 | Improved |
| add SRE and AWRE relation encoding | FastPitch w/ UAL · CNN/Daily Mail | MOS: 4.05 -> 4.15 | Improved |
| add SRE and AWRE relation encoding | FastPitch w/ UAL · CBT | MOS: 4.06 -> 4.15 | Improved |
| add SRE and AWRE relation encoding | FastPitch w/ UAL · OpenBookQA | MOS: 3.91 -> 4.00 | Improved |
| add SRE and AWRE relation encoding | FastPitch w/ UAL · SQuAD 2.0 | MOS: 4.10 -> 4.18 | Improved |
| add AWRE (ablation) | RWEN-BERT · CNN/Daily Mail | CMOS: -0.09 -> 0 | Improved |
| add SRE (ablation) | RWEN-BERT · CNN/Daily Mail | CMOS: -0.11 -> 0 | Improved |
| add SRE and AWRE (ablation) | FastPitch w/ UAL · CNN/Daily Mail | CMOS: -0.13 -> 0 | Improved |
| replace BERT-base with ELECTRA-base (ablation) | RWEN · CNN/Daily Mail | CMOS: +0.22 | Improved |
Closest papers by meaning
- EfficientTTS: An Efficient and High-Quality Text-to-Speech Architecture (ICML 2021 · similarity 0.85)
- Making the Relation Matters: Relation of Relation Learning Network for Sentence Semantic Matching (AAAI 2021 · similarity 0.85)
- CLaM-TTS: Improving Neural Codec Language Model for Zero-Shot Text-to-Speech (ICLR 2024 · similarity 0.85)
- DiTTo-TTS: Diffusion Transformers for Scalable Text-to-Speech without Domain-Specific Factors (ICLR 2025 · similarity 0.85)
- From Bytes to Ideas: Language Modeling with Autoregressive U-Nets (NeurIPS 2025 · similarity 0.84)
- NaturalSpeech 2: Latent Diffusion Models are Natural and Zero-Shot Speech and Singing Synthesizers (ICLR 2024 · similarity 0.84)
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.
