Papers with style control

7 papers
Versatile Framework for Song Generation with Prompt-based Control (2025.findings-emnlp)

Copied to clipboard

Challenge: Existing methods for song generation fail to generate vocals with prompt-based control and proper alignment.
Approach: VersBand is a multi-task song generation framework for synthesizing high-quality songs with prompt-based control.
Outcome: Experimental results show that VersBand performs better than baseline models across multiple song generation tasks.
TCSinger: Zero-Shot Singing Voice Synthesis with Style Transfer and Multi-Level Style Control (2024.emnlp-main)

Copied to clipboard

Challenge: Existing models fail to generate singing voices rich in stylistic nuances for unseen singers due to multifaceted nature of singing styles.
Approach: They propose a zero-shot SVS model for style transfer across cross-lingual speech and singing styles and multi-level style control.
Outcome: Experimental results show that TCSinger outperforms baseline models in synthesis quality, singer similarity, and style controllability.
Data-to-Text Generation with Style Imitation (2020.findings-emnlp)

Copied to clipboard

Challenge: Recent approaches to data-to-text generation focus on improving content fidelity, but lack explicit control over writing styles.
Approach: They propose a way to control writing styles by using existing sentences as "soft" templates . they conduct experiments in restaurants and sports domains to test their approach .
Outcome: The proposed approach achieves stronger performance than a range of comparison methods.
ReStyle-TTS: Relative and Continuous Style Control for Zero-Shot Speech Synthesis (2026.findings-acl)

Copied to clipboard

Challenge: Recent controllable zero-shot text-to-speech systems can synthesize speech for unseen speakers from a short reference audio clip, but they also inherit the speaking style present in the reference.
Approach: They propose a framework that enables continuous and reference-relative style control in zero-shot text-to-speech systems by combining style-specific LoRAs with Orthogonal LoRA Fusion.
Outcome: The proposed framework reduces the model's dependence on reference style while preserving text fidelity while maintaining intelligibility and speaker timbre.
TCSinger 2: Customizable Multilingual Zero-shot Singing Voice Synthesis (2025.findings-acl)

Copied to clipboard

Challenge: Existing zero-shot singing voice synthesis models depend on phoneme and note boundary annotations, limiting their robustness and producing poor transitions between phonemes and notes.
Approach: They propose a multi-task multilingual zero-shot SVS model with style transfer and style control based on various prompts.
Outcome: Experimental results show that TCSinger 2 outperforms baseline models in subjective and objective metrics across multiple related tasks.
Controllable Style Arithmetic with Language Models (2025.acl-long)

Copied to clipboard

Challenge: Existing methods for linguistic style control lack fine-grained control, require extensive computation, or introduce significant latency.
Approach: They propose a parameter-space approach that extracts style-specific representations by analyzing parameter differences between models trained on contrasting styles and incorporates them into a model with precise control over style intensity.
Outcome: The proposed approach achieves three key capabilities while achieving optimal computational efficiency.
FillerSpeech: Towards Human-Like Text-to-Speech Synthesis with Filler Insertion and Filler Style Control (2025.emnlp-main)

Copied to clipboard

Challenge: Recent advances in speech synthesis have improved audio quality and pronunciation . fillers are an integral part of natural human conversation, but achieving human-like conversational speech remains a challenge.
Approach: They propose a speech synthesis framework that enables natural filler insertion and style control . they propose 'filler-inclusive' speech data that includes fillers with pitch and duration information .
Outcome: The proposed framework enables natural filler insertion and style control . the proposed framework is validated and can be used to predict filler style .

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations