Multi-Dimensional Prosody Judgment For Live Streaming Speech Synthesis
cs.SD, cs.AI
Submitted: 2026-09-17
Updated: 2026-09-17
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- dots.tts Technical Report
- Comprehensive Benchmarking of Long-Form Speech Generation in Diverse Scenarios
- Evaluating the Expressive Appropriateness of Speech in Rich Contexts
- SpeechJudge: Towards Human-Level Judgment for Speech Naturalness
- GSRM: Generative Speech Reward Model for Speech RLHF
- UniSRM: A Unified Speech Reward Model for Reasoning-Based Fine-grained Assessment
- Gemini: A Family of Highly Capable Multimodal Models
- Qwen3-Omni Technical Report
- DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models
- Qwen3-TTS Technical Report
- CosyVoice: A Scalable Multilingual Zero-shot Text-to-speech Synthesizer based on Supervised Semantic Tokens
- IndexTTS2: A Breakthrough in Emotionally Expressive and Duration-Controlled Auto-Regressive Zero-Shot Text-to-Speech
- FireRedTTS: A Foundation Text-To-Speech Framework for Industry-Level Generative Speech Applications
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
- 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
- Efficient Audiovisual Speech Processing via MUTUD: Multimodal Training and Unimodal Deployment