Spotlight-TTS: Spotlighting the Style via Voiced-Aware Style Extraction and Style Direction Adjustment for Expressive Text-to-Speech
Not on the map. Why?
Abstract (arXiv)
Recent advances in expressive text-to-speech (TTS) have introduced diverse methods based on style embedding extracted from reference speech. However, synthesizing high-quality expressive speech remains challenging. We propose Spotlight-TTS, which exclusively emphasizes style via voiced-aware style extraction and style direction adjustment. Voiced-aware style extraction focuses on voiced regions highly related to style while maintaining continuity across different speech regions to improve expressiveness. We adjust the direction of the extracted style for optimal integration into the TTS model, which improves speech quality. Experimental results demonstrate that Spotlight-TTS achieves superior performance compared to baseline models in terms of expressiveness, overall speech quality, and style transfer capability. Our audio samples are publicly available.
Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 22 of its 31 references that are in the map. First posted on arXiv 27 May 2025.
Builds on
22 of 31 references.
References · 22
- 2017Attention Is All You Needcited by 60,361
- 2017Neural Discrete Representation Learningcited by 4,712
- 2022Robust Speech Recognition via Large-Scale Weak Supervisioncited by 4,057
- 2022A ConvNet for the 2020scited by 3,579
- 2016Gaussian Error Linear Units (GELUs)cited by 3,502
- 2013Estimating or Propagating Gradients Through Stochastic Neurons for Conditional Computationcited by 2,079
- 2021WavLM: Large-Scale Self-Supervised Pre-Training for Full Stack Speech Processingcited by 1,657
- 2022Autoregressive Image Generation using Residual Quantizationcited by 722
- 2020FastSpeech 2: Fast and High-Quality End-to-End Text to Speechcited by 717
- 2022UTMOS: UTokyo-SaruLab System for VoiceMOS Challenge 2022cited by 390
- 2018Style Tokens: Unsupervised Style Modeling, Control and Transfer in End-to-End Speech Synthesiscited by 259
- 2022BigVGAN: A Universal Neural Vocoder with Large-Scale Trainingcited by 251
10 more
- 2018Towards End-to-End Prosody Transfer for Expressive Speech Synthesis with Tacotroncited by 173
- 2021Emotional Voice Conversion: Theory, Databases and ESDcited by 115
- 2021Meta-StyleSpeech : Multi-Speaker Adaptive Text-to-Speech Generationcited by 93
- 2024Restructuring Vector Quantization with the Rotation Trickcited by 51
- 2023Not All Image Regions Matter: Masked Vector Quantization for Autoregressive Image Generationcited by 28
- 2024EmoSphere-TTS: Emotional Style and Intensity Modeling via Spherical Emotion Vector for Controllable Emotional Text-to-Speechcited by 24
- 2021Cross-speaker emotion disentangling and transfer for end-to-end speech synthesiscited by 21
- 2024TCSinger: Zero-Shot Singing Voice Synthesis with Style Transfer and Multi-Level Style Controlcited by 20
- 2022SyntaSpeech: Syntax-Aware Generative Adversarial Text-to-Speechcited by 18
- 2023QI-TTS: Questioning Intonation Control for Emotional Speech Synthesiscited by 8
Built on by
Citing papers per year: 2025: 1.
1 paper.