VoTSpeech: Decoupling Voice Design from Speech Generation in Instruction-Following TTS
cs.SD, cs.CL
Submitted: 2026-10-10
Updated: 2026-10-10
Code: https://github.com/ywbn/VoTSpeech
Terminology
Sources
- VoiceSculptor: Your Voice, Designed By You
- Ming-UniAudio: Speech LLM for Joint Understanding, Generation and Editing with Unified Representation
- Qwen3-TTS Technical Report
- MOSS-TTS Technical Report
- VoxCPM2 Technical Report
- CosyVoice: A Scalable Multilingual Zero-shot Text-to-speech Synthesizer based on Supervised Semantic Tokens
- MiniMax-Speech: Intrinsic Zero-Shot Text-to-Speech with a Learnable Speaker Encoder
- InstructTTSEval: Benchmarking Complex Natural-Language Instruction Following in Text-to-Speech Systems
- dots.tts Technical Report
- ISCSLP 2026 CoT-TTS Challenge: Chain-of-Thought Reasoning for Context-Aware Text-to-Speech
- Qwen3-Omni Technical Report
- DeepSeek-V4: Towards Highly Efficient Million-Token Context Intelligence
- Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities
Related papers
- Few-Shot Open-Set Audio Classification via Transductive Prototype Refinement and Class Logit Enhancement
- Spectral Masking and Interpolation Attack (SMIA): A Black-box Adversarial Attack against Voice Authentication and Anti-Spoofing Systems
- Remix the Timbre: Diffusion-Based Style Transfer Across Polyphonic Stems
- AVMeme Exam: A Multimodal Multilingual Multicultural Benchmark for LLMs' Contextual and Cultural Knowledge and Thinking
- SoundWeaver: Compositional Warm-Starting for Text-to-Audio Diffusion Serving
- WASIL: In-the-Wild Arabic Spoken Interactions with LLMs